Tootfinder

Japanese memory chipmaker Kioxia's stock falls 14% after a Bain Capital-backed entity sold $2.1B worth of shares at a discount, stoking AI valuation concerns (Bloomberg)
https://www.bloomberg.com/news/articles/2025-11-26…

Chipmaker Kioxia Sinks After Bain-Backed Firm Discloses Selloff
Kioxia Holdings Corp.’s shares dived more than 14% after a Bain Capital-backed entity unloaded $2.1 billion of shares in the Japanese memory chipmaker at a discount, stoking concerns about the lofty valuations of global AI-related firms.

Mastodon announced fiscal sponsorship via WE AID,
a German nonprofit organisation that supports charitable projects within an established legal framework.
This partnership offers donors
tax-deductible contributions in Germany
and ensures verified integrity through WE AID’s oversight.
It also enables Mastodon to operate as a nonprofit entity,
strengthening the commitment to a user-first,
community-driven platform,
free from algorithmic manipul…

Mastodon Joins Forces with WE AID
We're partnering with WE AID as our fiscal sponsor for donations in Europe.

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…

Mastodon announced fiscal sponsorship via WE AID,
a German nonprofit organisation that supports charitable projects within an established legal framework.
This partnership offers donors
tax-deductible contributions in Germany
and ensures verified integrity through WE AID’s oversight.
It also enables Mastodon to operate as a nonprofit entity,
strengthening the commitment to a user-first, community-driven platform,
free from algorithmic manipulation an…

Mastodon Joins Forces with WE AID
We're partnering with WE AID as our fiscal sponsor for donations in Europe.

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

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 Metro is alive. It breathes, it listens, it waits. It is not just tunnels and darkness, but a living, breathing entity that holds the souls of those who walk it and reveals truths only to those who are willing to see."
-- Сердар Искандеров
#MetroLastLight #Metro2033

A reminder that when you connect to JSTOR, you are connecting to an entity that generates tens of billions a year and that killed Aaron Swartz. #jstor

»TikTok signs deal for sale of U.S. unit after yearslong saga:
TikTok has signed a deal to divest its U.S. entity to a joint venture controlled by American investors, per an internal memo seen by Axios«
When will the children & young people (all people) finally realize that dss Internet is decentralized and not about a few power-hungry corporations?
(A rhetorical question in my dream of freedom)
🤷

Scoop: TikTok signs deal for U.S. unit after yearslong saga
The deal would end a yearslong saga to force TikTok's Chinese parent ByteDance to sell the company's U.S. operation.

RE: https://mastodon.social/@sarahjamielewis/115730052589989499
It is super expensive but it really seems to be time to think about how to create and fund an entity that can fork Firefox while Mozilla does some weird AI pie in the sky shit.

Internal memo: TikTok has signed a deal to sell its US unit; Oracle, Silver Lake, MGX will collectively own 45% of the US entity, and ByteDance will retain ~20% (Sara Fischer/Axios)
https://www.axios.com/2025/12/18/tiktok-sale

Scoop: TikTok signs deal for sale of U.S. unit after years-long saga
The deal would end a years-long saga to force TikTok's Chinese parent ByteDance to sell the company's U.S. operation.

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…

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…

"The Securing American Funding and Expertise from Adversarial Research Exploitation (SAFE) Act would deny federal funding to any U.S. scientist who collaborates with anyone “affiliated with a hostile foreign entity,” a category that includes four countries: China, Russia, Iran, and North Korea. The prohibited activities would include joint research, co-authorship on papers, and advising a foreign graduate student or postdoctoral fellow. The language is retroactive, meaning any interactions during the previous 5 years could make a scientist ineligible for future federal funding."
https://www.science.org/content/article/u-s-congress-considers-sweeping-ban-chinese-collaborations

@…
I can't tell if you're the same entity as the people adding so-called AI to Firefox, are you? Or can you pass a message on?
My message would be: Firefox would be much more valuable as a privacy-first, climate-conscious, efficient alternative to the other browsers jumping on the LLM bandwagon.
#Firefox #Mozilla

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

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…

In Canada, the CBC might be the kind of entity to help run / coordinate “public service social media” as described in this Tech Policy Press article https://www.techpolicy.press/public-service-social-media-as-a-democratic-safeguard/
With interop…

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

Internal memo: TikTok has signed a deal to sell its US unit; Oracle, Silver Lake, MGX will collectively own 45% of the US entity, and ByteDance will retain ~20% (Sara Fischer/Axios)
https://www.axios.com/2025/12/18/tiktok-sale

Scoop: TikTok signs deal for sale of U.S. unit after years-long saga
The deal would end a years-long saga to force TikTok's Chinese parent ByteDance to sell the company's U.S. operation.

This CSO letter submitted today has a single #China/#HongKong entity, China Labour Bulletin.
Which self-dissolved in mid-2025...
https://foejapan.org/en/issue/20251205/27117/

Call for the Suspension of Irresponsible Nickel Development in Palawan, the Philippines — More Than a Decade Without Effective Environmental Measures, Leaving Community Rights at Risk — International Petition (8,411 Signatories from 36 Countries; 90 Organizations from 40 Countries) Submitted to Sumitomo Metal Mining | Friends of the Earth Japan
Ahead of Human Rights Day on December 10, an international petition calling for the suspe...

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
Uro\v{s} \v{S}majdek, Ciril Bohak
https://arxiv.org/abs/2510.04971 https://

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
We present an interactive visualization system for exploring named entities and their relationships across document collections. The system is designed around a graph-based representation that integrates three types of nodes: documents, entity mentions, and entities. Connections capture two key relationship types: (i) identical entities across contexts, and (ii) co-locations of mentions within documents. Multiple coordinated views enable users to examine entity occurrences, discover clusters of…

hardware iceberg, near the top:
- nobody can implement I2C in hardware (except for Philips)
- SPI doesn't exist as a coherent entity
- UART has a CDR loop but you don't think of it that way
- MSP430 "JTAG" 🦋

The retreat of US military from Europe is long overdue and a blessing in disguise, Europe should be able to defend itself without the help of the US in the future. NATO should be replaced by an European defence entity.
#eu #defence

Sony Pictures Entertainment and Sony Music Entertainment (Japan) agree to buy WildBrain's 41% stake in Peanuts Holdings for ~$457M, raising Sony's slice to 80% (Todd Spangler/Variety)
https://variety.com/2025/film/news/sony-acquire-peanuts-457-mil…

Sony to Own Control of Peanuts in $457 Million Deal With WildBrain
Sony will own 80% of Peanuts Holdings after acquiring the 41% stake in the entity from WildBrain.

So this is percolating and the results so far are not surprising.
I'd vote NO, for the following reasons:
- oil demand continues to decline and risk is high we'll end up with an expensive underutilized pipeline. Therefore high risk we'll end up subsidizing any private entity that builds this thing.
- why would we invest public dollars to support infrastructure for a product where 75% of the profit leaves Canada? There has to be a net benefit, beyond steel sales and jobs, for this project to be considered.
- Indigenous land rights must be respected. They will be left with the rusting pipeline decades in the future, and it's impact on the land.
- the B.C. government must also have a final vote as they have to give up land and provide support.
- we don't need additional oil tankers on our west coast.
- and most importantly, with this MOU, Canada pretty much declared we aren't serious about protecting the environment or fighting climate change. We're oil whores. Harsh but....
#CanPoli #ClimateAction

"Archaeologists: D.C. Capitol May Once Have Been Used For Legislating"

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
Minhao Qiao, Iqbal Gondal, Hai Dong
https://arxiv.org/abs/2510.12153 https://

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
Cross chain interoperability in blockchain systems exposes a fundamental tension between user privacy and regulatory accountability. Existing solutions enforce an all or nothing choice between full anonymity and mandatory identity disclosure, which limits adoption in regulated financial settings. We present VeilAudit, a cross chain auditing framework that introduces Auditor Only Linkability, which allows auditors to link transaction behaviors that originate from the same anonymous entity withou…

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

@… TIL:
<https://en.wikipedia.org/wiki/Jumping_the_shark>
＂… a creative work or entity has evolved and reached a point in which it has exh…

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…

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…

Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity
Eric Tillmann Bill, Enis Simsar, Thomas Hofmann
https://arxiv.org/abs/2510.02315 https://

Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity
Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-subject descriptions, often showing attribute leakage, identity entanglement, and subject omissions. We introduce the first theoretical framework with a principled, optimizable objective for steering sampling dynamics toward multi-subject fidelity. Viewing flow matching (FM) through stochastic optimal control (SOC), we formulate subject disentanglement as control over a trained FM sampler. This yields two architec…

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

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…

Replaced article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new
[1/1]:
- FastER: On-Demand Entity Resolution in Property Graphs
Wang, Zhao, Miao, Kwashie, Bewong, Hu, Nofong, Feng
…

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

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
Pratik Shah, Rajat Ghosh, Aryan Singhal, Debojyoti Dutta
https://arxiv.org/abs/2509.25257 https://

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities, or natural language queries (for example, describing a task and retrieving the corresponding code…

President Trump says Netflix's planned acquisition of WBD will have "to go through a process", as it would create an entity with "a lot of market share" (Bloomberg)
https://www.bloomberg.com/news/articles/2025-12…

🇺🇦 #NowPlaying on KEXP's #VarietyMix
DJ Trace:
🎵 Lost Entity (Harmony Remix)
#DJTrace
#newRelease 🆕 single
https://deepjungle.bandcamp.com/track/dj-trace-lost-entity-london-side
https://open.spotify.com/track/4m1Ttkc0YGnEWy3HYUjvBl

Researchers find Predator spyware is being used in several countries, including Iraq https://therecord.media/intellexa-predator-spyware-continues-despite-sanctions

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 …

Can LLMs Hit Moving Targets? Tracking Evolving Signals in Corporate Disclosures
Chanyeol Choi, Jihoon Kwon, Minjae Kim
https://arxiv.org/abs/2510.03195 https://

Can LLMs Hit Moving Targets? Tracking Evolving Signals in Corporate Disclosures
Moving targets -- managers' strategic shifting of key performance metrics when the original targets become difficult to achieve -- have been shown to predict subsequent stock underperformance. However, our work reveals that the method employed in that study exhibits two key limitations that hinder the accuracy -- noise in the extracted targets and loss of contextual information -- both of which stem primarily from the use of a named entity recognition (NER). To address these two limitations, we…

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…

President Trump says Netflix's planned acquisition of WBD will have "to go through a process", as it would create an entity with "a lot of market share" (Bloomberg)
https://www.bloomberg.com/news/articles/2025-12…

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

Alt5 Sigma accumulated $1.5 billion of World Liberty Financial cryptocurrency in August as part of a circular deal that routed more than an estimated $500 million to an entity affiliated with President Donald Trump
Public companies, like Alt5 Sigma, must notify the SEC within four business days when their independent accountant resigns, and their accountant must reviewany interim financial statements included in a quarterly report.
Alt5 Sigma told the SEC on Black Friday its indep…

Trump Crypto Partner Alt5 Sigma May Have Violated SEC Rules After Another Filing Discrepancy
Alt5 Sigma told regulators its accountant resigned in November, while he says he notified the company three months earlier.

BNP Paribas says it is joining nine other European banks including ING, UniCredit, and CaixaBank developing a euro-pegged stablecoin in a JV called Qivalis (CoinDesk)
https://www.coindesk.com/business/2025/12/02/bnp…

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

Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
Guan-Ting Lin, Shih-Yun Shan Kuan, Jiatong Shi, Kai-Wei Chang, Siddhant Arora, Shinji Watanabe, Hung-yi Lee
https://arxiv.org/abs/2510.07838

Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
While full-duplex speech agents enable natural, low-latency interaction by speaking and listening simultaneously, their consistency and task performance in multi-turn settings remain underexplored. We introduce Full-Duplex-Bench-v2 (FDB-v2), a streaming framework that integrates with an automated examiner that enforces staged goals under two pacing setups (Fast vs. Slow). FDB-v2 covers four task families: daily, correction, entity tracking, and safety. We report turn-taking fluency, multi-turn …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/6]:
- Query Brand Entity Linking in E-Commerce Search
Dong Liu, Sreyashi Nag
https://

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

The Netflix-WBD deal should quiet concerns, for now, from CNN employees worried about the prospect of Paramount combining CBS News and CNN in a WBD acquisition (John Koblin/New York Times)
https://www.nytimes.com/2025/12/05/business/media/cnn-net…

CNN Is Excluded From Netflix’s Warner Bros. Deal for Now
The prospect of Paramount’s buying Warner Bros. Discovery had led CNN journalists to wonder if the channel may be combined with CBS News. Instead, CNN will remain in a separate corporate entity.

SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
Ehsan Aghaei, Sarthak Jain, Prashanth Arun, Arjun Sambamoorthy
https://arxiv.org/abs/2510.00240 https://…

SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
Effective analysis of cybersecurity and threat intelligence data demands language models that can interpret specialized terminology, complex document structures, and the interdependence of natural language and source code. Encoder-only transformer architectures provide efficient and robust representations that support critical tasks such as semantic search, technical entity extraction, and semantic analysis, which are key to automated threat detection, incident triage, and vulnerability assessm…

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

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Wenjie Zhang
https://arxiv.org/abs/2510.12434

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, w…

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

Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer
Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense
https://arxiv.org/abs/2510.03202 https://…

Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer
We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual models and two tasks: part-of-speech tagging (POS) and named entity recognition (NER). We consider 51 source languages and evaluate on 56 and 72 target languages for POS and NER, respectively. When using in-domain data, NN-Rank beats state-of-the-art baselines t…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/5]:
- Medical Question Summarization with Entity-driven Contrastive Learning
Wenpeng Lu, Sibo Wei, Xueping Peng, Yi-fei Wang, Usman Naseem, Shoujin Wang