Tootfinder

Generative Annotation for ASR Named Entity Correction
Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang, Hao Yang
https://arxiv.org/abs/2508.20700

Generative Annotation for ASR Named Entity Correction
End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been proposed in recent years. These models, mainly leveraging phonetic-level edit distance algorithms, have shown impressive performances. However, when the forms of the wrongly-transcribed words(s) and the ground-truth entity are significantly different, these methods …

dbpedia_location: DBpedia entity-location network
A bipartite network of the affiliations between named entities from Wikipedia and particular notable locations, as extracted from Wikipedia by the DBpedia project. The date of this snapshot is uncertain.
This network has 225498 nodes and 293697 edges.
Tags: Informational, Relatedness, Unweighted

“What we seem to have here is yet another instance of a massive corporate entity capitulating to the emperor’s wishes in advance, but this one is particularly frustrating because there is less for the average consumer like you and me to do about it.” https://apple.news/AIOs-uVO9S62q7E2-cg0v2A

We Should All Be Uneasy About Apple TV+ Pulling ‘The Savant’ from Its Lineup — Esquire
This is seemingly another instance of a massive corporate entity capitulating to the emperor’s wishes in advance—but this one is particularly frustrating.

The US Commerce Department says subsidiaries of entity list companies would also be subject to trade restrictions, threatening Chinese companies, from Tuesday (Amrith Ramkumar/Wall Street Journal)
https://www.

The strikes on the Venezuelan boats
-- allegedly carrying "narcotics"
-- which the administration has claimed were necessary because interdiction "did not work,"
have been orchestrated through the homeland security council (HSC)
-- which Stephen Miller leads
as the homeland security adviser.
Miller empowered the HSC earlier this year to become its own entity in Donald Trump’s second term
-- a notable departure from previous administ…

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy
Haibo Wang, Lutfu S. Sua, Jun Huang, Figen Balo, Burak Dolar
https://arxiv.org/abs/2509.22381

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy
Effective credit risk management is fundamental to financial decision-making, necessitating robust models for default probability prediction and financial entity classification. Traditional machine learning approaches face significant challenges when confronted with high-dimensional data, limited interpretability, rare event detection, and multi-class imbalance problems in risk assessment. This research proposes a comprehensive meta-learning framework that synthesizes multiple complementary mod…

Sources: Saudi Arabia's PIF is the largest contributor to the $36B in equity used to finance the EA deal; it will roll over its $5B EA stake into the new entity (Bloomberg)
https://www.bloomberg.com/news/articles/2025-09-29/s…

InfoAgent: Advancing Autonomous Information-Seeking Agents
Gongrui Zhang, Jialiang Zhu, Ruiqi Yang, Kai Qiu, Miaosen Zhang, Zhirong Wu, Qi Dai, Bei Liu, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Yuan Zhang, Xin Li, Zhaoyi Liu, Xin Geng, Baining Guo
https://arxiv.org/abs/2509.25189…

InfoAgent: Advancing Autonomous Information-Seeking Agents
Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we introduce InfoAgent, a deep research agent powered by an innovative data synthesis pipeline and orchestrated web search tools. To construct challenging, hard-to-find queries,we build entity trees and apply sub-tree sampling with entity fuzzification to systematically increase question difficulty. Unlike prior work tha…

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- FoodSEM: Large Language Model Specialized in Food Named-Entity Linking
Gjorgjevikj, Martinc, Cenikj, D\v{z}eroski, Seljak, Eftimov

Named Entity Recognition of Historical Text via Large Language Model
Shibingfeng Zhang, Giovanni Colavizza
https://arxiv.org/abs/2508.18090 https://arxiv.o…

Named Entity Recognition of Historical Text via Large Language Model
Large language models have demonstrated remarkable versatility across a wide range of natural language processing tasks and domains. One such task is Named Entity Recognition (NER), which involves identifying and classifying proper names in text, such as people, organizations, locations, dates, and other specific entities. NER plays a crucial role in extracting information from unstructured textual data, enabling downstream applications such as information retrieval from unstructured text. Tr…

The Quasi-Creature and the Uncanny Valley of Agency: A Synthesis of Theory and Evidence on User Interaction with Inconsistent Generative AI
Mauricio Manhaes, Christine Miller, Nicholas Schroeder
https://arxiv.org/abs/2508.18563

The Quasi-Creature and the Uncanny Valley of Agency: A Synthesis of Theory and Evidence on User Interaction with Inconsistent Generative AI
The user experience with large-scale generative AI is paradoxical: superhuman fluency meets absurd failures in common sense and consistency. This paper argues that the resulting potent frustration is an ontological problem, stemming from the "Quasi-Creature"-an entity simulating intelligence without embodiment or genuine understanding. Interaction with this entity precipitates the "Uncanny Valley of Agency," a framework where user comfort drops when highly agentic AI proves erratically unreliab…

Oh you thought the ordeal of being perceived was mortifying? Wait 'till you try being perceived by a state.
As its bureaucratic gaze lingers through the entrails of your medical, financial, scholastic, and social records, a deep disquiet oozes through your brain upon consideration of the labyrinthine antagonisms it may—or may not—inflict upon you. In service only to Capital, this entity has bequeathed immeasurable portions of suffering and death to those it threatens to protect, let alone to its ever-multiplying enemies, and now it is your turn to be found wanting, for in its incessant mechanical hunger, wanting is all that the state can conceive of.
#horror #capitalism #nationalism

White House says TikTok's new US entity would lease a copy of ByteDance's algorithm, which Oracle would retrain; US users wouldn't need to re-download the app (Axios)
https://www.axios.com/2025/09/22/tiktok-bytedance-trump-algorithm-lease

Inside Trump's deal to save TikTok
TikTok's new U.S. entity would lease its algorithm from Chinese owner ByteDance.

On Multi-entity, Multivariate Quickest Change Point Detection
Bahar Kor, Bipin Gaikwad, Abani Patra, Eric L. Miller
https://arxiv.org/abs/2509.18310 https://

On Multi-entity, Multivariate Quickest Change Point Detection
We propose a framework for online Change Point Detection (CPD) from multi-entity, multivariate time series data, motivated by applications in crowd monitoring where traditional sensing methods (e.g., video surveillance) may be infeasible. Our approach addresses the challenge of detecting system-wide behavioral shifts in complex, dynamic environments where the number and behavior of individual entities may be uncertain or evolve. We introduce the concept of Individual Deviation from Normality (I…

Exploring the Theory and Practice of Concurrency in the Entity-Component-System Pattern
Patrick Redmond, Jonathan Castello, Jos\'e Manuel Calder\'on Trilla, Lindsey Kuper
https://arxiv.org/abs/2508.15264

Exploring the Theory and Practice of Concurrency in the Entity-Component-System Pattern
The Entity-Component-System (ECS) software design pattern, long used in game development, encourages a clean separation of identity (entities), data properties (components), and computational behaviors (systems). Programs written using the ECS pattern are naturally concurrent, and the pattern offers modularity, flexibility, and performance benefits that have led to a proliferation of ECS frameworks. Nevertheless, the ECS pattern is little-known and not well understood outside of a few domains. …

Crosslisted article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new
[1/1]:
- Database Entity Recognition with Data Augmentation and Deep Learning
Zikun Fu, Chen Yang, Kourosh Davoudi, Ken Q. Pu

Mah\={a}n\={a}ma: A Unique Testbed for Literary Entity Discovery and Linking
Sujoy Sarkar, Gourav Sarkar, Manoj Balaji Jagadeeshan, Jivnesh Sandhan, Amrith Krishna, Pawan Goyal
https://arxiv.org/abs/2509.19844

Mahānāma: A Unique Testbed for Literary Entity Discovery and Linking
High lexical variation, ambiguous references, and long-range dependencies make entity resolution in literary texts particularly challenging. We present Mahānāma, the first large-scale dataset for end-to-end Entity Discovery and Linking (EDL) in Sanskrit, a morphologically rich and under-resourced language. Derived from the Mahābhārata, the world's longest epic, the dataset comprises over 109K named entity mentions mapped to 5.5K unique entities, and is aligned with an English knowledge base…

Sources: data integration company Fivetran is in talks to acquire data management company dbt Labs in a deal valuing the combined entity at between $5B and $10B (The Information)
https://www.theinformation.com/articles/data-startup-fi…

Data Startup Fivetran In Talks to Buy Dbt Labs in Multibillion Dollar Deal
Fivetran, a startup used by companies to manage and prepare data for analytics and artificial intelligence, is in talks to buy data management companydbt Labs, according to people with direct knowledge of the deal. The deal would combine two data companies that are facing competition from ...

An LLM ASP Workflow for Joint Entity-Relation Extraction
Trang Tran, Trung Hoang Le, Huiping Cao, Tran Cao Son
https://arxiv.org/abs/2508.12611 https://a…

An LLM + ASP Workflow for Joint Entity-Relation Extraction
Joint entity-relation extraction (JERE) identifies both entities and their relationships simultaneously. Traditional machine-learning based approaches to performing this task require a large corpus of annotated data and lack the ability to easily incorporate domain specific information in the construction of the model. Therefore, creating a model for JERE is often labor intensive, time consuming, and elaboration intolerant. In this paper, we propose harnessing the capabilities of generative pre…

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Pengcheng Fang, Yuxia Chen, Rui Guo
https://arxiv.org/abs/2508.15641 https…

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic reasoning, they remain coarse in temporal perception: timestamps are encoded only implicitly, frame level features are weak in capturing continuity, and language vision alignment often drifts from the entities of interest. In this paper, we present Grounded VideoDi…

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Haoran Luo, Haihong E, Guanting Chen, Qika Lin, Yikai Guo, Fangzhi Xu, Zemin Kuang, Meina Song, Xiaobao Wu, Yifan Zhu, Luu Anh Tuan
https://arxiv.org/abs/2507.21892

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, an agentic GraphRAG framework via end-to-end reinforcement …

Feds allege Bolton mishandled classified info and was hacked by "foreign entity" (Dave Lawler/Axios)
https://www.axios.com/2025/09/12/fbi-bolton-hack-foreign-entity-documents-probe
http://www.memeorandum.com/250912/p136#a250912p136

https://www.stirworld.com/think-opinions-remaking-the-chinese-garden-a-contemporary-architectural-dilemma

Remaking the Chinese Garden: a contemporary architectural dilemma
The Chinese garden is not just a single, independent entity built for crafting landscapes or modelling nature itself, it is a lexicon of symbols, layered upon built reality.

Overview of BioASQ 2024: The twelfth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara, Salvador Lima-L\'opez, Eul\`alia Farr\'e-Maduell, Martin Krallinger, Natalia Loukachevitch, Vera Davydova, Elena Tutubalina, Georgios Paliouras
https://

Overview of BioASQ 2024: The twelfth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
This is an overview of the twelfth edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2024. BioASQ is a series of international challenges promoting advances in large-scale biomedical semantic indexing and question answering. This year, BioASQ consisted of new editions of the two established tasks b and Synergy, and two new tasks: a) MultiCardioNER on the adaptation of clinical entity detection to the cardiology domain in a multilingual sett…

Oracle, which already provides computing resources for TikTok, would lead “data and privacy” for the new entity.
White House Outlines a TikTok Deal With a U.S. Board
https://www.nytimes.com/2025/09/20/technology/white-house-tiktok-deal.html

White House Outlines a TikTok Deal With a U.S. Board
A potential deal to reduce TikTok’s ties to China would give the app a new board with six American directors out of seven, the White House press secretary said.

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Inference Gap in Domain Expertise and Machine Intelligence in Named Entity Recognition: Creation ...
Sumon Kanti Dey, Jeanne M. Powell, Azra Ismail, Jeanmarie Perrone, Abeed Sarker

Transformer-Gather, Fuzzy-Reconsider: A Scalable Hybrid Framework for Entity Resolution
Mohammadreza Sharifi, Danial Ahmadzadeh
https://arxiv.org/abs/2509.17470 https://

Transformer-Gather, Fuzzy-Reconsider: A Scalable Hybrid Framework for Entity Resolution
Entity resolution plays a significant role in enterprise systems where data integrity must be rigorously maintained. Traditional methods often struggle with handling noisy data or semantic understanding, while modern methods suffer from computational costs or the excessive need for parallel computation. In this study, we introduce a scalable hybrid framework, which is designed to address several important problems, including scalability, noise robustness, and reliable results. We utilized a pre…

Overview of BioASQ 2025: The Thirteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara, Martin Krallinger, Miguel Rodr\'iguez-Ortega, Eduard Rodriguez-L\'opez, Natalia Loukachevitch, Andrey Sakhovskiy, Elena Tutubalina, Dimitris Dimitriadis, Grigorios Tsoumakas, George Giannakoulas, Alexandra Bekiaridou, Athanasios Samaras, Giorgio Maria Di Nunzio, Nicola Ferro, Stefano Marchesin, …

Overview of BioASQ 2025: The Thirteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
This is an overview of the thirteenth edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2025. BioASQ is a series of international challenges promoting advances in large-scale biomedical semantic indexing and question answering. This year, BioASQ consisted of new editions of the two established tasks, b and Synergy, and four new tasks: a) Task MultiClinSum on multilingual clinical summarization. b) Task BioNNE-L on nested named entity linkin…

Innovative Distributed Maintenance Concept: From the design to cost optimisation
Maria Di Mascolo (G-SCOP, G-SCOP\_DOME2S), Zineb Simeu-Abazi (G-SCOP, G-SCOP\_DOME2S), Rony Ars\`ene Djeunang Mezafack (G-SCOP, G-SCOP\_DOME2S)
https://arxiv.org/abs/2508.16160

Innovative Distributed Maintenance Concept: From the design to cost optimisation
This study proposes an integrated heuristic framework for the strategic optimization of distributed maintenance operations in geo-distributed production systems (GDPS). It introduces a dual-entity maintenance structure comprising a Centralized Maintenance Workshop (CMW) and a Mobile Maintenance Workshop (MMW), aimed at minimizing total long-term maintenance costs. The cost function incorporates transport, operations, and downtime penalties, optimized via a two-stage algorithmic approach: a Main…

Trustworthy Semantic Communication for Vehicular Networks: Challenges and Solutions
Yanghe Pan, Yuntao Wang, Shaolong Guo, Chengyu Yin, Ruidong Li, Zhou Su, Yuan Wu
https://arxiv.org/abs/2509.20830

Trustworthy Semantic Communication for Vehicular Networks: Challenges and Solutions
Semantic communication (SemCom) has the potential to significantly reduce communication delay in vehicle-to-everything (V2X) communications within vehicular networks (VNs). However, the deployment of vehicular SemCom networks (VN-SemComNets) faces critical trust challenges in information transmission, semantic encoding, and communication entity reliability. This paper proposes an innovative three-layer trustworthy VN-SemComNet architecture. Specifically, we introduce a semantic camouflage trans…

dbpedia_location: DBpedia entity-location network
A bipartite network of the affiliations between named entities from Wikipedia and particular notable locations, as extracted from Wikipedia by the DBpedia project. The date of this snapshot is uncertain.
This network has 225498 nodes and 293697 edges.
Tags: Informational, Relatedness, Unweighted

White House says TikTok's new US entity would lease a copy of the algorithm from ByteDance, which Oracle would retrain; users won't need to re-download the app (Axios)
https://www.axios.com/2025/09/22/tiktok-bytedance-trump-algorithm-lease

Inside Trump's deal to save TikTok
TikTok's new U.S. entity would lease its algorithm from Chinese owner ByteDance.

It was a challenging week for Americans that strongly assert that organisations enforcing their own standards to supress speech cannot be censorship, even if that action is as a result of backroom coercion from a more powerful entity that may or may not be a government.

The next question after Turing's question: Introducing the Grow-AI test
Alexandru Tugui
https://arxiv.org/abs/2508.16277 https://arxiv.org/pdf/2508.162…

The next question after Turing's question: Introducing the Grow-AI test
This study aims to extend the framework for assessing artificial intelligence, called GROW-AI (Growth and Realization of Autonomous Wisdom), designed to answer the question "Can machines grow up?" -- a natural successor to the Turing Test. The methodology applied is based on a system of six primary criteria (C1-C6), each assessed through a specific "game", divided into four arenas that explore both the human dimension and its transposition into AI. All decisions and actions of the entity are re…

I could have written "maybe we rely a bit too much on these giant server farms owned by a single entity?" but I like the more silly and less serious approach to the discussion.
Beside, writing it here I'm just preaching the quire. So we might have some fun meanwhile!

Got this email and thought, "Ha that is a scam. There is no way that the real Paypal would provide a link to update to login and card details!" 🤣
I mean they are a well known entity, with a well known domain, they can just tell you to do it. It's not like you don't know the URL.
But no, that is exactly what they have done. 🤯
P.S. Paypal, yes I know but sometimes it is the only way to pay. 😢

D-party congress critters ought to begin drafting bills to dismantle DHS.
DHS, including its highly nazi-flavored name, was constructed by a Congress and president (bush) who were terrified after 9/11.
It is time to pull the pieces of DHS apart, retaining some parts, deleting other parts (such as ICE), and reshaping the rest.
There is a rule of thumb that suggests that if one wants to re-form an entity to change its internal culture that no more than 10% of the staff should…

Crosslisted article(s) found for cs.MA. https://arxiv.org/list/cs.MA/new
[1/1]:
- DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
Fang Wang, Tianwei Yan, Zonghao Yang, Minghao Hu, Jun Zhang, Zhunchen Luo, Xiaoying Bai

On Evaluating the Adversarial Robustness of Foundation Models for Multimodal Entity Linking
Fang Wang, Yongjie Wang, Zonghao Yang, Minghao Hu, Xiaoying Bai
https://arxiv.org/abs/2508.15481

On Evaluating the Adversarial Robustness of Foundation Models for Multimodal Entity Linking
The explosive growth of multimodal data has driven the rapid development of multimodal entity linking (MEL) models. However, existing studies have not systematically investigated the impact of visual adversarial attacks on MEL models. We conduct the first comprehensive evaluation of the robustness of mainstream MEL models under different adversarial attack scenarios, covering two core tasks: Image-to-Text (I2T) and Image+Text-to-Text (IT2T). Experimental results show that current MEL models gen…

Human-Annotated NER Dataset for the Kyrgyz Language
Timur Turatali, Anton Alekseev, Gulira Jumalieva, Gulnara Kabaeva, Sergey Nikolenko
https://arxiv.org/abs/2509.19109 https://…

A Taxonomy and Methodology for Proof-of-Location Systems
Eduardo Brito, Fernando Castillo, Liina Kamm, Amnir Hadachi, Ulrich Norbisrath
https://arxiv.org/abs/2508.14230 https://…

A Taxonomy and Methodology for Proof-of-Location Systems
Digital societies increasingly rely on trustworthy proofs of physical presence for services such as supply-chain tracking, e-voting, ride-sharing, and location-based rewards. Yet, traditional localization methods often lack cryptographic guarantees of where and when an entity was present, leaving them vulnerable to spoofing, replay, or collusion attacks. In response, research on Proof-of-Location (PoL) has emerged, with recent approaches combining distance bounding, distributed consensus, and p…

The National Association of Broadcasters and several broadcasting companies urge the FCC to end its rule capping the number of TV stations an entity can own (Jennifer Maas/Variety)
https://variety.com/2025/tv/news/broadcaster-fcc-abolish-nation…

Broadcasters Call for FCC to Abolish National TV Ownership Rule
The National Association of Broadcasters (NAB) and several broadcast companies called for a repel of the FCC's national TV ownership rule.

My guess here at a distance is that it’s a terrible mistake to think of “Harvard” as a single anthropomorphic entity with a single mind. There are surely terrible internal battles raging at Harvard right now: between those who think it’s truly for education and those who think it’s truly for ROI, between those protecting the dollars and those protecting the brand reputation, between those cowering at the short-term financial risk of angering an authoritarian and those who see the long-term risks of capitulating.
What does “Harvard” think? Harvard is a bunch of different people. I wish them luck, and wisdom. Heaven knows they’ll need it.
/end

At this point, I’m not sure whether it’s better to warn people about buying a Tesla or not. Sure, people die horribly in them. But also, the only people buying a Tesla today are either full-on Nazis or people for whom fascism isn’t a deal breaker, so… 🤷‍♂️ https://raggedfeathers.com/@lilithsain

DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
Fang Wang, Tianwei Yan, Zonghao Yang, Minghao Hu, Jun Zhang, Zhunchen Luo, Xiaoying Bai
https://arxiv.org/abs/2508.15876

DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse cross-modal fusion, and the difficulty of jointly large language models (LLMs) and large visual models (LVMs). To address these issues, we propose DeepMEL, a novel framework based on multi-agent collaborative reasoning, which achieves efficient alignment and disambigu…

Ground-Based Radar Tracking of Near-Earth Objects With VLBI Radio Telescopes: 2024 MK Test Case
Oliver White, Guifr\'e Molera Calv\'es, Shinji Horiuchi, Ed Kruzins, Edwin Peters, Nick Stacy
https://arxiv.org/abs/2509.15684

Ground-Based Radar Tracking of Near-Earth Objects With VLBI Radio Telescopes: 2024 MK Test Case
The Southern Hemisphere Asteroid Research Project is an active and informal entity comprising the University of New South Wales, the University of Tasmania, the University of Western Australia, and the Curtin University, which performs asteroid research in collaboration with federal agencies, including the Commonwealth Scientific and Industrial Research Organisation and the National Aeronautics and Space Administration (JPL). Since 2015, we have used the Australian infrastructure to characteriz…

Nothing plans to invest $100M to spin off budget brand CMF into an independent subsidiary, with India as its manufacturing and R&D headquarters (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/09/24/smartphone-maker-nothing-to-spin-off-…

Smartphone maker Nothing to spin off its affordable CMF brand | TechCrunch
Nothing is making its affordable devices brand CMF into a separate entity with headquarters in India.

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury, Michael Cochez, Martijn Schut
https://arxiv.org/abs/2508.13663

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Methods for query answering over incomplete knowledge graphs retrieve entities that are likely to be answers, which is particularly useful when such answers cannot be reached by direct graph traversal due to missing edges. However, existing approaches have focused on queries formalized using first-order-logic. In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories. Addressing this gap, we …

In light of the ongoing enshittification of #GitHub and the inevitable expansion to #npm, I'm delighted to see that although founded by the commercial entity behind #Deno,

Advances in Logic-Based Entity Resolution: Enhancing ASPEN with Local Merges and Optimality Criteria
Zhliang Xiang, Meghyn Bienvenu, Gianluca Cima, V\'ictor Guti\'errez-Basulto, Yazm\'in Ib\'a\~nez-Garc\'ia
https://arxiv.org/abs/2508.10504

Advances in Logic-Based Entity Resolution: Enhancing ASPEN with Local Merges and Optimality Criteria
In this paper, we present ASPEN+, which extends an existing ASP-based system, ASPEN,for collective entity resolution with two important functionalities: support for local merges and new optimality criteria for preferred solutions. Indeed, ASPEN only supports so-called global merges of entity-referring constants (e.g. author ids), in which all occurrences of matched constants are treated as equivalent and merged accordingly. However, it has been argued that when resolving data values, local merg…

dbpedia_location: DBpedia entity-location network
A bipartite network of the affiliations between named entities from Wikipedia and particular notable locations, as extracted from Wikipedia by the DBpedia project. The date of this snapshot is uncertain.
This network has 225498 nodes and 293697 edges.
Tags: Informational, Relatedness, Unweighted

What makes an entity salient in discourse?
Amir Zeldes, Jessica Lin
https://arxiv.org/abs/2508.16464 https://arxiv.org/pdf/2508.16464

What makes an entity salient in discourse?
Entities in discourse vary broadly in salience: main participants, objects and locations are noticeable and memorable, while tangential ones are less important and quickly forgotten, raising questions about how humans signal and infer relative salience. Using a graded operationalization of salience based on summary-worthiness in multiple summaries of a discourse, this paper explores data from 24 spoken and written genres of English to extract a multifactorial complex of overt and implicit lingu…

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Shubham Chatterjee, Jeff Dalton
https://arxiv.org/abs/2510.11589 https://

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representa…

The next question after Turing's question: Introducing the Grow-AI test
Alexandru Tugui
https://arxiv.org/abs/2508.16277 https://arxiv.org/pdf/2508.162…

The next question after Turing's question: Introducing the Grow-AI test
This study aims to extend the framework for assessing artificial intelligence, called GROW-AI (Growth and Realization of Autonomous Wisdom), designed to answer the question "Can machines grow up?" -- a natural successor to the Turing Test. The methodology applied is based on a system of six primary criteria (C1-C6), each assessed through a specific "game", divided into four arenas that explore both the human dimension and its transposition into AI. All decisions and actions of the entity are re…

OpenAI sets up a legal entity, and plans to open its first office in India after launching ChatGPT Go, its cheapest plan, in the country on August 19 (Munsif Vengattil/Reuters)
https://www.reuters.com/world/india/openai-launch-first-india-…

GenCNER: A Generative Framework for Continual Named Entity Recognition
Yawen Yang, Fukun Ma, Shiao Meng, Aiwei Liu, Lijie Wen
https://arxiv.org/abs/2510.11444 https://

GenCNER: A Generative Framework for Continual Named Entity Recognition
Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. However, existing continual learning (CL) methods for NER face challenges of catastrophic forgetting and semantic shift of non-entity type. In this paper, we propose GenCNER, a simple but effective Generative framework for CNER to mitigate the above dra…

Understanding Fanchuan in Livestreaming Platforms: A New Form of Online Antisocial Behavior
Yiluo Wei, Jiahui He, Gareth Tyson
https://arxiv.org/abs/2509.00780 https://

Understanding Fanchuan in Livestreaming Platforms: A New Form of Online Antisocial Behavior
Recently, a distinct form of online antisocial behavior, known as "fanchuan", has emerged across online platforms, particularly in livestreaming chats. Fanchuan is an indirect attack on a specific entity, such as a celebrity, video game, or brand. It entails two main actions: (i) individuals first feign support for the entity, and exhibit this allegiance widely; (ii) they then engage in offensive or irritating behavior, attempting to undermine the entity by association. This deceptive conduct i…

A Robust and Efficient Pipeline for Enterprise-Level Large-Scale Entity Resolution
Sandeepa Kannangara, Arman Abrahamyan, Daniel Elias, Thomas Kilby, Nadav Dar, Luiz Pizzato, Anna Leontjeva, Dan Jermyn
https://arxiv.org/abs/2508.03767

A Robust and Efficient Pipeline for Enterprise-Level Large-Scale Entity Resolution
Entity resolution (ER) remains a significant challenge in data management, especially when dealing with large datasets. This paper introduces MERAI (Massive Entity Resolution using AI), a robust and efficient pipeline designed to address record deduplication and linkage issues in high-volume datasets at an enterprise level. The pipeline's resilience and accuracy have been validated through various large-scale record deduplication and linkage projects. To evaluate MERAI's performance, we compare…

CrossDenoise: Denoising Implicit Feedback via a Lightweight Entity-Aware Synergistic Framework
Ze Liu, Xianquan Wang, Shuochen Liu, Jie Ma, Huibo Xu, Yupeng Han, Zhe Yang, Kai Zhang, Longfei Li, Jun Zhou
https://arxiv.org/abs/2508.10851

CrossDenoise: Denoising Implicit Feedback via a Lightweight Entity-Aware Synergistic Framework
Recommender systems heavily rely on implicit feedback, which is inherently noisy due to false positives and negatives, severely degrading recommendation accuracy. Existing denoising strategies often overlook entity-aware modeling, suffer from high computational overhead, or demand excessive hyperparameter tuning, limiting their real-world applicability. We propose CrossDenoise, a novel and lightweight framework that addresses these challenges by disentangling noise estimation into user-, item-,…

dbpedia_location: DBpedia entity-location network
A bipartite network of the affiliations between named entities from Wikipedia and particular notable locations, as extracted from Wikipedia by the DBpedia project. The date of this snapshot is uncertain.
This network has 225498 nodes and 293697 edges.
Tags: Informational, Relatedness, Unweighted

Dynamic Span Interaction and Graph-Aware Memory for Entity-Level Sentiment Classification
Md. Mithun Hossain, Sanjara, Md. Shakil Hossain, Sudipto Chaki
https://arxiv.org/abs/2509.11604

Dynamic Span Interaction and Graph-Aware Memory for Entity-Level Sentiment Classification
Entity-level sentiment classification involves identifying the sentiment polarity linked to specific entities within text. This task poses several challenges: effectively modeling the subtle and complex interactions between entities and their surrounding sentiment expressions; capturing dependencies that may span across sentences; and ensuring consistent sentiment predictions for multiple mentions of the same entity through coreference resolution. Additionally, linguistic phenomena such as nega…

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
Or Shachar, Uri Katz, Yoav Goldberg, Oren Glickman
https://arxiv.org/abs/2509.04011 https://

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval, a variant of Named Entity Recognition (NER), where the types of interest are not provided in advance, and a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on internal representations of large language models (LLMs) to embed both entity mentions and user-provided open-ended type desc…

Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
Kalana Wijegunarathna, Kristin Stock, Christopher B. Jones
https://arxiv.org/abs/2508.06584

Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
The development, integration, and maintenance of geospatial databases rely heavily on efficient and accurate matching procedures of Geospatial Entity Resolution (ER). While resolution of points-of-interest (POIs) has been widely addressed, resolution of entities with diverse geometries has been largely overlooked. This is partly due to the lack of a uniform technique for embedding heterogeneous geometries seamlessly into a neural network framework. Existing neural approaches simplify complex ge…

EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
Zirui Liao
https://arxiv.org/abs/2510.08958 https://arxiv.org/pdf/2510.08958

EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
Cognitive neuroscience research indicates that humans leverage cues to activate entity-centered memory traces (engrams) for complex, multi-hop recollection. Inspired by this mechanism, we introduce EcphoryRAG, an entity-centric knowledge graph RAG framework. During indexing, EcphoryRAG extracts and stores only core entities with corresponding metadata, a lightweight approach that reduces token consumption by up to 94\% compared to other structured RAG systems. For retrieval, the system first ex…

British renewable energy startup Octopus Energy spins off its AI arm, Kraken, in what could create a stand-alone entity worth $15B (Yusuf Khan/Wall Street Journal)
https://www.wsj.com/articles/octopus-energy-to-s…

BIBERT-Pipe on Biomedical Nested Named Entity Linking at BioASQ 2025
Chunyu Li, Xindi Zheng, Siqi Liu
https://arxiv.org/abs/2509.09725 https://arxiv.org/pd…

BIBERT-Pipe on Biomedical Nested Named Entity Linking at BioASQ 2025
Entity linking (EL) for biomedical text is typically benchmarked on English-only corpora with flat mentions, leaving the more realistic scenario of nested and multilingual mentions largely unexplored. We present our system for the BioNNE 2025 Multilingual Biomedical Nested Named Entity Linking shared task (English & Russian), closing this gap with a lightweight pipeline that keeps the original EL model intact and modifies only three task-aligned components: Two-stage retrieval-ranking. We lever…

Leveraging Large Language Models for Rare Disease Named Entity Recognition
Nan Miles Xi, Yu Deng, Lin Wang
https://arxiv.org/abs/2508.09323 https://arxiv.o…

Leveraging Large Language Models for Rare Disease Named Entity Recognition
Named Entity Recognition (NER) in the rare disease domain poses unique challenges due to limited labeled data, semantic ambiguity between entity types, and long-tail distributions. In this study, we evaluate the capabilities of GPT-4o for rare disease NER under low-resource settings, using a range of prompt-based strategies including zero-shot prompting, few-shot in-context learning, retrieval-augmented generation (RAG), and task-level fine-tuning. We design a structured prompting framework tha…

The NYDFS grants Bullish a BitLicense, allowing its US entity to offer spot trading and custody services in the state (CoinDesk)
https://www.coindesk.com/policy/2025/09/17/crypto-platform-bullish-wins-new-york-bitlic…

ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval
Zihan Chen, Lei Shi, Weize Wu, Qiji Zhou, Yue Zhang
https://arxiv.org/abs/2509.07512

ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval
Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a b…

TASER: Table Agents for Schema-guided Extraction and Recommendation
Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso
https://arxiv.org/abs/2508.13404 …

TASER: Table Agents for Schema-guided Extraction and Recommendation
Real-world financial documents report essential information about an entity's financial holdings that can span millions of different financial instrument types. Yet, these details are often buried in messy, multi-page, fragmented tables - for example, 99.4% of the tables in our dataset have no bounding boxes with the maximum number of rows amounting to 426 per table across 44 pages. To tackle these unique challenges from real-world tables, we present a continuously learning, agentic table extra…

Query-Centric Graph Retrieval Augmented Generation
Yaxiong Wu, Jianyuan Bo, Yongyue Zhang, Sheng Liang, Yong Liu
https://arxiv.org/abs/2509.21237 https://a…

Query-Centric Graph Retrieval Augmented Generation
Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained entity-level graphs incur high token costs and lose context, while coarse document-level graphs fail to capture nuanced relations. We introduce QCG-RAG, a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval. Our query-cen…

REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
Shubham Chatterjee
https://arxiv.org/abs/2510.11592 https://arxiv.org/pd…

REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted texts. While humans naturally anchor their understanding around key entities and concepts, neural models process text within rigid token windows, treating all interactions as equally important and missing critical semantic signals. We introduce REGENT, a neural…

Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction
Lei Hei, Tingjing Liao, Yingxin Pei, Yiyang Qi, Jiaqi Wang, Ruiting Li, Feiliang Ren
https://arxiv.org/abs/2509.21151

Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction
Relation extraction (RE) aims to identify semantic relations between entities in unstructured text. Although recent work extends traditional RE to multimodal scenarios, most approaches still adopt classification-based paradigms with fused multimodal features, representing relations as discrete labels. This paradigm has two significant limitations: (1) it overlooks structural constraints like entity types and positional cues, and (2) it lacks semantic expressiveness for fine-grained relation und…

How Larry Ellison is focusing his philanthropic efforts on the Ellison Institute of Technology, an Oxford-based, for-profit entity set to spend £1B by 2027 (New York Times)
https://www.nytimes.com/2025/08/12/business/larry-ellison-oracle-philanthropy.html…

Larry Ellison Wants to Do Good, Do Research and Make a Profit
Oracle’s co-founder and the world’s second-richest person pledges to concentrate his vast resources on his own research institute and for-profit ventures to address health, hunger and climate change.

Decoupled Entity Representation Learning for Pinterest Ads Ranking
Jie Liu, Yinrui Li, Jiankai Sun, Kungang Li, Han Sun, Sihan Wang, Huasen Wu, Siyuan Gao, Paulo Soares, Nan Li, Zhifang Liu, Haoyang Li, Siping Ji, Ling Leng, Prathibha Deshikachar
https://arxiv.org/abs/2509.04337

Decoupled Entity Representation Learning for Pinterest Ads Ranking
In this paper, we introduce a novel framework following an upstream-downstream paradigm to construct user and item (Pin) embeddings from diverse data sources, which are essential for Pinterest to deliver personalized Pins and ads effectively. Our upstream models are trained on extensive data sources featuring varied signals, utilizing complex architectures to capture intricate relationships between users and Pins on Pinterest. To ensure scalability of the upstream models, entity embeddings are …

DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph
Debayan Banerjee, Tilahun Abedissa Taffa, Ricardo Usbeck
https://arxiv.org/abs/2507.22811 https://…

DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph
In this work we present an entity linker for DBLP's 2025 version of RDF-based Knowledge Graph. Compared to the 2022 version, DBLP now considers publication venues as a new entity type called dblp:Stream. In the earlier version of DBLPLink, we trained KG-embeddings and re-rankers on a dataset to produce entity linkings. In contrast, in this work, we develop a zero-shot entity linker using LLMs using a novel method, where we re-rank candidate entities based on the log-probabilities of the "yes" t…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

Exploring Stability-Plasticity Trade-offs for Continual Named Entity Recognition
Duzhen Zhang, Chenxing Li, Jiahua Dong, Qi Liu, Dong Yu
https://arxiv.org/abs/2508.03259 https:/…

Exploring Stability-Plasticity Trade-offs for Continual Named Entity Recognition
Continual Named Entity Recognition (CNER) is an evolving field that focuses on sequentially updating an existing model to incorporate new entity types. Previous CNER methods primarily utilize Knowledge Distillation (KD) to preserve prior knowledge and overcome catastrophic forgetting, strictly ensuring that the representations of old and new models remain consistent. Consequently, they often impart the model with excessive stability (i.e., retention of old knowledge) but limited plasticity (i.e…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
KM Pooja, Cheng Long, Aixin Sun
https://arxiv.org/abs/2510.02726 https://

PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
The task of entity linking, which involves associating mentions with their respective entities in a knowledge graph, has received significant attention due to its numerous potential applications. Recently, various multimodal entity linking (MEL) techniques have been proposed, targeted to learn comprehensive embeddings by leveraging both text and vision modalities. The selection of high-quality negative samples can potentially play a crucial role in metric/representation learning. However, to th…

PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
Jiajun He, Naoki Sawada, Koichi Miyazaki, Tomoki Toda
https://arxiv.org/abs/2509.04357 https…

PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-grained phoneme variations due to limited entity diversity. Moreover, prior methods treat entities as independent tokens, leading to incomplete multi-token biasing. To address these issues, we propose Phoneme-Augmented Robust Contextual ASR via COntrastive entity disambiguation (PARCO), which integrates phoneme-aware …

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP
Decheng Duan, Yingyi Zhang, Jitong Peng, Chengzhi Zhang
https://arxiv.org/abs/2509.07801

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP
Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While existing datasets aid model development, most focus on specific publication sections due to domain complexity and the high cost of annotating scientific texts. To address this limitation, we introduce SciNLP - a specialized benchmark for full-text entity and relation extraction in the Natural Language Processing (NLP) domain. The dataset comprises …

Is 'Hope' a person or an idea? A pilot benchmark for NER: comparing traditional NLP tools and large language models on ambiguous entities
Payam Latifi
https://arxiv.org/abs/2509.12098

Is 'Hope' a person or an idea? A pilot benchmark for NER: comparing traditional NLP tools and large language models on ambiguous entities
This pilot study presents a small-scale but carefully annotated benchmark of Named Entity Recognition (NER) performance across six systems: three non-LLM NLP tools (NLTK, spaCy, Stanza) and three general-purpose large language models (LLMs: Gemini-1.5-flash, DeepSeek-V3, Qwen-3-4B). The dataset contains 119 tokens covering five entity types (PERSON, LOCATION, ORGANIZATION, DATE, TIME). We evaluated each system's output against the manually annotated gold standard dataset using F1-score. The res…

WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives
Daniel Brubaker, William Sheffield, Junyi Jessy Li, Kanishka Misra
https://arxiv.org/abs/2510.09556

WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives
The role of world knowledge has been particularly crucial to predict the discourse connective that marks the discourse relation between two arguments, with language models (LMs) being generally successful at this task. We flip this premise in our work, and instead study the inverse problem of understanding whether discourse connectives can inform LMs about the world. To this end, we present WUGNECTIVES, a dataset of 8,880 stimuli that evaluates LMs' inferences about novel entities in contexts w…

Towards Adaptive Context Management for Intelligent Conversational Question Answering
Manoj Madushanka Perera, Adnan Mahmood, Kasun Eranda Wijethilake, Quan Z. Sheng
https://arxiv.org/abs/2509.17829

Towards Adaptive Context Management for Intelligent Conversational Question Answering
This particular paper introduces an Adaptive Context Management (ACM) framework for the Conversational Question Answering (ConvQA) systems. The key objective of the ACM framework is to optimize the use of the conversation history by dynamically managing context for maximizing the relevant information provided to a ConvQA model within its token limit. Our approach incorporates a Context Manager (CM) Module, a Summarization (SM) Module, and an Entity Extraction (EE) Module in a bid to handle the …

SciEvent: Benchmarking Multi-domain Scientific Event Extraction
Bofu Dong, Pritesh Shah, Sumedh Sonawane, Tiyasha Banerjee, Erin Brady, Xinya Du, Ming Jiang
https://arxiv.org/abs/2509.15620

SciEvent: Benchmarking Multi-domain Scientific Event Extraction
Scientific information extraction (SciIE) has primarily relied on entity-relation extraction in narrow domains, limiting its applicability to interdisciplinary research and struggling to capture the necessary context of scientific information, often resulting in fragmented or conflicting statements. In this paper, we introduce SciEvent, a novel multi-domain benchmark of scientific abstracts annotated via a unified event extraction (EE) schema designed to enable structured and context-aware unde…

NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
Huhong Xian, Rui Liu, Berrak Sisman, Haizhou Li
https://arxiv.org/abs/2509.03829

NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
Different from traditional sentence-level audio deepfake detection (ADD), partial audio deepfake detection (PADD) requires frame-level positioning of the location of fake speech. While some progress has been made in this area, leveraging semantic information from audio, especially named entities, remains an underexplored aspect. To this end, we propose NE-PADD, a novel method for Partial Audio Deepfake Detection (PADD) that leverages named entity knowledge through two parallel branches: Speech …

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
David Demitri Africa, Suchir Salhan, Yuval Weiss, Paula Buttery, Richard Diehl Martinez
https://arxiv.org/abs/2509.02160

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
Named-entity recognition (NER) in low-resource languages is usually tackled by finetuning very large multilingual LMs, an option that is often infeasible in memory- or latency-constrained settings. We ask whether small decoder LMs can be pretrained so that they adapt quickly and transfer zero-shot to languages unseen during pretraining. To this end we replace part of the autoregressive objective with first-order model-agnostic meta-learning (MAML). Tagalog and Cebuano are typologically similar …

Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition
Mayur Shirke, Amey Shembade, Pavan Thorat, Madhushri Wagh, Raviraj Joshi
https://arxiv.org/abs/2509.02514

Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition
Named Entity Recognition (NER) in code-mixed text, particularly Hindi-English (Hinglish), presents unique challenges due to informal structure, transliteration, and frequent language switching. This study conducts a comparative evaluation of code-mixed fine-tuned models and non-code-mixed multilingual models, along with zero-shot generative large language models (LLMs). Specifically, we evaluate HingBERT, HingMBERT, and HingRoBERTa (trained on code-mixed data), and BERT Base Cased, IndicBERT, R…

Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
Wuyang Zhang, Yexin Tian, Xiandong Meng, Mengjie Wang, Junliang Du
https://arxiv.org/abs/2508.14427

Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm framework based on knowledge graph injection. The method builds on pretrained language models and introduces structured graph information for auxiliary learning. A graph neural network is used to encode entities and their relations, constructing a graph-based sema…

On the Representations of Entities in Auto-regressive Large Language Models
Victor Morand, Josiane Mothe, Benjamin Piwowarski
https://arxiv.org/abs/2510.09421 https://

On the Representations of Entities in Auto-regressive Large Language Models
Named entities are fundamental building blocks of knowledge in text, grounding factual information and structuring relationships within language. Despite their importance, it remains unclear how Large Language Models (LLMs) internally represent entities. Prior research has primarily examined explicit relationships, but little is known about entity representations themselves. We introduce entity mention reconstruction as a novel framework for studying how LLMs encode and manipulate entities. We …

DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
Yupei Yang, Fan Feng, Lin Yang, Wanxi Deng, Lin Qu, Biwei Huang, Shikui Tu, Lei Xu
https://arxiv.org/abs/2508.14391

DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
Relation extraction enables the construction of structured knowledge for many downstream applications. While large language models (LLMs) have shown great promise in this domain, most existing methods concentrate on relation classification, which predicts the semantic relation type between a related entity pair. However, we observe that LLMs often struggle to reliably determine whether a relation exists, especially in cases involving complex sentence structures or intricate semantics, which lea…

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala
https://arxiv.org/abs/2507.22744

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
Reducing hallucinations in abstractive summarization remains a critical challenge for deploying language models (LMs) in real-world settings. In this work, we introduce a rewarddriven fine-tuning framework that explicitly optimizes for Entity Hallucination Index (EHI), a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries. Given a corpus of meeting transcripts, we first generate baseline summaries using a pre-trained LM and compute EHI s…

Using LLMs for Multilingual Clinical Entity Linking to ICD-10
Sylvia Vassileva, Ivan Koychev, Svetla Boytcheva
https://arxiv.org/abs/2509.04868 https://arx…

Using LLMs for Multilingual Clinical Entity Linking to ICD-10
The linking of clinical entities is a crucial part of extracting structured information from clinical texts. It is the process of assigning a code from a medical ontology or classification to a phrase in the text. The International Classification of Diseases - 10th revision (ICD-10) is an international standard for classifying diseases for statistical and insurance purposes. Automatically assigning the correct ICD-10 code to terms in discharge summaries will simplify the work of healthcare prof…

Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
Duygu Altinok
https://arxiv.org/abs/2508.13376 https://arxiv.org/pdf/2508.1…

Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by distilling contextual knowledge from LLaMA models into Whisper. Our method uses two strategies: (1) token level distillation with optimal transport to align dimensions and sequence lengths, and (2) representation loss minimization between sentence embeddings of…

Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling
Insaf Nahri, Romain Pinqui\'e, Philippe V\'eron, Nicolas Bus, Mathieu Thorel
https://arxiv.org/abs/2508.13833

Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling
This study explores the integration of Building Information Modeling (BIM) with Natural Language Processing (NLP) to automate the extraction of requirements from unstructured French Building Technical Specification (BTS) documents within the construction industry. Employing Named Entity Recognition (NER) and Relation Extraction (RE) techniques, the study leverages the transformer-based model CamemBERT and applies transfer learning with the French language model Fr\_core\_news\_lg, both pre-trai…

An LLM Agent-Based Complex Semantic Table Annotation Approach
Yilin Geng, Shujing Wang, Chuan Wang, Keqing He, Yanfei Lv, Ying Wang, Zaiwen Feng, Xiaoying Bai
https://arxiv.org/abs/2508.12868

An LLM Agent-Based Complex Semantic Table Annotation Approach
The Semantic Table Annotation (STA) task, which includes Column Type Annotation (CTA) and Cell Entity Annotation (CEA), maps table contents to ontology entities and plays important roles in various semantic applications. However, complex tables often pose challenges such as semantic loss of column names or cell values, strict ontological hierarchy requirements, homonyms, spelling errors, and abbreviations, which hinder annotation accuracy. To address these issues, this paper proposes an LLM-bas…

Weakly Supervised Medical Entity Extraction and Linking for Chief Complaints
Zhimeng Luo, Zhendong Wang, Rui Meng, Diyang Xue, Adam Frisch, Daqing He
https://arxiv.org/abs/2509.01899

Weakly Supervised Medical Entity Extraction and Linking for Chief Complaints
A Chief complaint (CC) is the reason for the medical visit as stated in the patient's own words. It helps medical professionals to quickly understand a patient's situation, and also serves as a short summary for medical text mining. However, chief complaint records often take a variety of entering methods, resulting in a wide variation of medical notations, which makes it difficult to standardize across different medical institutions for record keeping or text mining. In this study, we propose …

HistoryBankQA: Multilingual Temporal Question Answering on Historical Events
Biswadip Mandal, Anant Khandelwal, Manish Gupta
https://arxiv.org/abs/2509.12720 https://

HistoryBankQA: Multilingual Temporal Question Answering on Historical Events
Temporal reasoning about historical events is a critical skill for NLP tasks like event extraction, historical entity linking, temporal question answering, timeline summarization, temporal event clustering and temporal natural language inference. Yet efforts on benchmarking temporal reasoning capabilities of large language models (LLMs) are rather limited. Existing temporal reasoning datasets are limited in scale, lack multilingual coverage and focus more on contemporary events. To address thes…