Tootfinder

I've published a detailed article about #ChatGPT hallucination minimization using predefined #SPARQL-based query templates scoped to Linked Open Data (LOD) Cloud Knowledge Graphs such as #UniProtKB…

Reducing Hallucinations in ChatGPT using Predefined Query Templates scoped to Knowledge Graphs
In the fast-paced world of artificial intelligence, chatbots using language model strategies are becoming more common. However, these chatbots sometimes generate responses based on incorrect or fabricated information, a problem often referred to as “hallucinations.

Redefining Information Retrieval of Structured Database via Large Language Models
Mingzhu Wang, Yuzhe Zhang, Qihang Zhao, Juanyi Yang, Hong Zhang
https://arxiv.org/abs/2405.05508 …

Redefining Information Retrieval of Structured Database via Large Language Models
Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside the query, enhancing the reliability of responses towards factual questions. Prior researches in retrieval augmentation typically follow a retriever-generator paradigm. In this context, traditional retrievers encounter challenges in precisely and seamlessly ex…

This https://arxiv.org/abs/2404.19232 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

GRAMMAR: Grounded and Modular Evaluation of Domain-Specific Retrieval-Augmented Language Models
Retrieval-augmented Generation (RAG) systems have been actively studied and deployed across various industries to query on domain-specific knowledge base. However, evaluating these systems presents unique challenges due to the scarcity of domain-specific queries and corresponding ground truths, as well as a lack of systematic approaches to diagnosing the cause of failure cases -- whether they stem from knowledge deficits or issues related to system robustness. To address these challenges, we in…

Redefining Information Retrieval of Structured Database via Large Language Models
Mingzhu Wang, Yuzhe Zhang, Qihang Zhao, Juanyi Yang, Hong Zhang
https://arxiv.org/abs/2405.05508 …

Redefining Information Retrieval of Structured Database via Large Language Models
Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside the query, enhancing the reliability of responses towards factual questions. Prior researches in retrieval augmentation typically follow a retriever-generator paradigm. In this context, traditional retrievers encounter challenges in precisely and seamlessly ex…

Great! #Google has a meta-fact check search engine!
This query returns results in all languages; the default is to return only your browser language, but you can change between them and other languages.
h/t/ @…

NL2KQL: From Natural Language to Kusto Query
Amir H. Abdi, Xinye Tang, Jeremias Eichelbaum, Mahan Das, Alex Klein, Nihal Irmak Pakis, William Blum, Daniel L Mace, Tanvi Raja, Namrata Padmanabhan, Ye Xing
https://arxiv.org/abs/2404.02933

NL2KQL: From Natural Language to Kusto Query
Data is growing rapidly in volume and complexity. Proficiency in database query languages is pivotal for crafting effective queries. As coding assistants become more prevalent, there is significant opportunity to enhance database query languages. The Kusto Query Language (KQL) is a widely used query language for large semi-structured data such as logs, telemetries, and time-series for big data analytics platforms. This paper introduces NL2KQL an innovative framework that uses large language mod…

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, Yitao Liang
https://arxiv.org/abs/2403.05313

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated…

Great! #Google has a meta-fact check search engine!
This query returns results in all languages; the default is to return only your browser language, but you can change between them and other languages.
h/t/ @…

"But RDBMS require more than just a query language; C. J. Date introduced the concept of referential integrity in 1981, and Jim Gray the idea of transactions and ACID in 1983–no, not the acid that Steve Jobs was recommending to Bill Gates to drop, but the one you read about in database books, about atomicity, consistency, isolation, and durability."

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Lihui Liu, Zihao Wang, Ruizhong Qiu, Yikun Ban, Hanghang Tong
https://arxiv.org/abs/2404.04264

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Despite the superb performance in many tasks, large language models (LLMs) bear the risk of generating hallucination or even wrong answers when confronted with tasks that demand the accuracy of knowledge. The issue becomes even more noticeable when addressing logic queries that require multiple logic reasoning steps. On the other hand, knowledge graph (KG) based question answering methods are capable of accurately identifying the correct answers with the help of knowledge graph, yet its accurac…

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, Yitao Liang
https://arxiv.org/abs/2403.05313

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated…

Web developer: my dynamically typed language is now faster than that other dynamically typed language. Sometimes. By a small amount.
Also web developer: SELECT query in loop.

This https://arxiv.org/abs/2403.00867 has been replaced.
link: https://scholar.google.com/scholar?q=a

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced training techniques such as Reinforcement Learning from Human Feedback (RLHF). However, recent studies have highlighted the vulnerability of LLMs to adversarial jailbreak attempts aiming at subverting the embedded safety guardrails. To address this challenge, t…

Learning Phonotactics from Linguistic Informants
Canaan Breiss, Alexis Ross, Amani Maina-Kilaas, Roger Levy, Jacob Andreas
https://arxiv.org/abs/2405.04726

Learning Phonotactics from Linguistic Informants
We propose an interactive approach to language learning that utilizes linguistic acceptability judgments from an informant (a competent language user) to learn a grammar. Given a grammar formalism and a framework for synthesizing data, our model iteratively selects or synthesizes a data-point according to one of a range of information-theoretic policies, asks the informant for a binary judgment, and updates its own parameters in preparation for the next query. We demonstrate the effectiveness o…

GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation
Kaustubh Dhole, Eugene Agichtein
https://arxiv.org/abs/2404.03746 https:…

GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation
Query Reformulation(QR) is a set of techniques used to transform a user's original search query to a text that better aligns with the user's intent and improves their search experience. Recently, zero-shot QR has been shown to be a promising approach due to its ability to exploit knowledge inherent in large language models. By taking inspiration from the success of ensemble prompting strategies which have benefited many tasks, we investigate if they can help improve query reformulation. In this…

Make Data Analysis Easy with Custom GPTs #ChatGPT #AI: https://tceajmg.micro.blog/2024/05/01/

Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models
Hongyi Zhu, Jia-Hong Huang, Stevan Rudinac, Evangelos Kanoulas
https://arxiv.org/abs/2404.18746

Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models
Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics. Conventional image search systems operate by accepting textual or visual queries, retrieving the top-relevant candidate results from the database. However, prevalent methods often rely on single-turn procedures, introducing potential inaccuracies and limited recall. These methods also face the challenges, such as vocabulary mi…

GUing: A Mobile GUI Search Engine using a Vision-Language Model
Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais, Binbin Xu, Pierre Louis Bernard, G\'erard Dray, Walid Maalej
https://arxiv.org/abs/2405.00145

GUing: A Mobile GUI Search Engine using a Vision-Language Model
App developers use the Graphical User Interface (GUI) of other apps as an important source of inspiration to design and improve their own apps. In recent years, research suggested various approaches to retrieve GUI designs that fit a certain text query from screenshot datasets acquired through automated GUI exploration. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements in the screenshots, neglecting visual information such as icons or backg…

Learning Phonotactics from Linguistic Informants
Canaan Breiss, Alexis Ross, Amani Maina-Kilaas, Roger Levy, Jacob Andreas
https://arxiv.org/abs/2405.04726

Learning Phonotactics from Linguistic Informants
We propose an interactive approach to language learning that utilizes linguistic acceptability judgments from an informant (a competent language user) to learn a grammar. Given a grammar formalism and a framework for synthesizing data, our model iteratively selects or synthesizes a data-point according to one of a range of information-theoretic policies, asks the informant for a binary judgment, and updates its own parameters in preparation for the next query. We demonstrate the effectiveness o…

Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategies
Zheng Ning, Yuan Tian, Zheng Zhang, Tianyi Zhang, Toby Li
https://arxiv.org/abs/2402.07304

Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategies
Querying structured databases with natural language (NL2SQL) has remained a difficult problem for years. Recently, the advancement of machine learning (ML), natural language processing (NLP), and large language models (LLM) have led to significant improvements in performance, with the best model achieving ~85% percent accuracy on the benchmark Spider dataset. However, there is a lack of a systematic understanding of the types, causes, and effectiveness of error-handling mechanisms of errors for…

PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning
Simon Holk, Daniel Marta, Iolanda Leite
https://arxiv.org/abs/2402.15420

PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning
Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However, formulating realistic policies for robots demands responses from humans to an extensive array of queries. In this work, we approach the sample-efficiency challenge by expanding the information collected per query to contain both preferences and optional text prompting…

LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
Zhaodonghui Li, Haitao Yuan, Huiming Wang, Gao Cong, Lidong Bing
https://arxiv.org/abs/2404.12872

LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
Query rewrite, which aims to generate more efficient queries by altering a SQL query's structure without changing the query result, has been an important research problem. In order to maintain equivalence between the rewritten query and the original one during rewriting, traditional query rewrite methods always rewrite the queries following certain rewrite rules. However, some problems still remain. Firstly, existing methods of finding the optimal choice or sequence of rewrite rules are still l…

I got access to Gemini million dollar token thing.
Here is what I found it useful for. I dumped the whole text of “Ethnic cleansing of Palestine” a book I read years ago. There are tons of details that I cant recall anymore.
I am using it like a database that you can query with natural language “what were the cities that were targeted by plan Dalet”. It is truly great for this. Or run more complex queries.
Not my idea, I first saw Joe Heitzeberg do this with his persona…

This https://arxiv.org/abs/2402.17652 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Navigator: A Decentralized Scheduler for Latency-Sensitive ML Workflows
We consider ML query processing in distributed systems where GPU-enabled workers coordinate to execute complex queries: a computing style often seen in applications that interact with users in support of image processing and natural language processing. In such systems, coscheduling of GPU memory management and task placement represents a promising opportunity. We propose Navigator, a novel framework that unifies these functions to reduce job latency while using resources efficiently, placing t…

What’s especially interesting is that Don Chamberlin isn’t just some random IBMer (https://en.wikipedia.org/wiki/Donald_D._Chamberlin). And he wasn’t only involved with Quill SGML editor, but also with the Quilt XML query language, which heavily influenced XQuery (he was o…

What’s especially interesting is that Don Chamberlin isn’t just some random IBMer (https://en.wikipedia.org/wiki/Donald_D._Chamberlin). And he wasn’t only involved with Quill SGML editor, but also with the Quilt XML query language, which heavily influenced XQuery (he was o…

This https://arxiv.org/abs/2309.08730 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train …

This https://arxiv.org/abs/2403.18276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism -- attention requires $O(n^2)$ time complexity in training and $O(n)$ time complexity in inference. Many works have been proposed to improve the attention mechanism's scalability, such as Flash Attention and Multi-query Attention. A different line of work aims t…

Language Fairness in Multilingual Information Retrieval
Eugene Yang, Thomas J\"anich, James Mayfield, Dawn Lawrie
https://arxiv.org/abs/2405.00978 htt…

Language Fairness in Multilingual Information Retrieval
Multilingual information retrieval (MLIR) considers the problem of ranking documents in several languages for a query expressed in a language that may differ from any of those languages. Recent work has observed that approaches such as combining ranked lists representing a single document language each or using multilingual pretrained language models demonstrate a preference for one language over others. This results in systematic unfair treatment of documents in different languages. This work …

This https://arxiv.org/abs/2404.02933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

NL2KQL: From Natural Language to Kusto Query
Data is growing rapidly in volume and complexity. Proficiency in database query languages is pivotal for crafting effective queries. As coding assistants become more prevalent, there is significant opportunity to enhance database query languages. The Kusto Query Language (KQL) is a widely used query language for large semi-structured data such as logs, telemetries, and time-series for big data analytics platforms. This paper introduces NL2KQL an innovative framework that uses large language mod…

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
Yixin Cheng, Markos Georgopoulos, Volkan Cevher, Grigorios G. Chrysos
https://arxiv.org/abs/2402.09177

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly challenging for Jailbreaking attacks. In this work, inspired by human practices of indirect context to elicit harmful information, we focus on a new attack form called Contextual Interaction Attack. The idea relies on the autoregressive nature of the generatio…

This https://arxiv.org/abs/2402.16567 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Aligning Large Language Models to a Domain-specific Graph Database
Graph Databases (Graph DB) are widely applied in various fields, including finance, social networks, and medicine. However, translating Natural Language (NL) into the Graph Query Language (GQL), commonly known as NL2GQL, proves to be challenging due to its inherent complexity and specialized nature. Some approaches have sought to utilize Large Language Models (LLMs) to address analogous tasks like text2SQL. Nevertheless, when it comes to NL2GQL taskson a particular domain, the absence of domain…

This https://arxiv.org/abs/2306.08266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csFL_…

Analyzing Robustness of Angluin's L$^*$ Algorithm in Presence of Noise
Angluin's L$^*$ algorithm learns the minimal deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by numerous random membership queries to get a high level confidence to the answer. Thus it can be applied to any kind of device and may be viewed as an algorithm for synthesizing an automaton abstracting the behavior of the device based on observations. Here we a…

Navigator: A Decentralized Scheduler for Latency-Sensitive ML Workflows
Yuting Yang, Andrea Merlina, Weijia Song, Tiancheng Yuan, Ken Birman, Roman Vitenberg
https://arxiv.org/abs/2402.17652

Navigator: A Decentralized Scheduler for Latency-Sensitive ML Workflows
We consider ML query processing in distributed systems where GPU-enabled workers coordinate to execute complex queries: a computing style often seen in applications that interact with users in support of image processing and natural language processing. In such systems, coscheduling of GPU memory management and task placement represents a promising opportunity. We propose Navigator, a novel framework that unifies these functions to reduce job latency while using resources efficiently, placing t…

Query Rewriting via Large Language Models
Jie Liu, Barzan Mozafari
https://arxiv.org/abs/2403.09060 https://arxiv.org/pdf/2403.09060<…

Query Rewriting via Large Language Models
Query rewriting is one of the most effective techniques for coping with poorly written queries before passing them down to the query optimizer. Manual rewriting is not scalable, as it is error-prone and requires deep expertise. Similarly, traditional query rewriting algorithms can only handle a small subset of queries: rule-based techniques do not generalize to new query patterns and synthesis-based techniques cannot handle complex queries. Fortunately, the rise of Large Language Models (LLMs),…

Tailoring Education with GenAI: A New Horizon in Lesson Planning
Kostas Karpouzis, Dimitris Pantazatos, Joanna Taouki, Kalliopi Meli
https://arxiv.org/abs/2403.12071

Tailoring Education with GenAI: A New Horizon in Lesson Planning
The advent of Generative AI (GenAI) in education presents a transformative approach to traditional teaching methodologies, which often overlook the diverse needs of individual students. This study introduces a GenAI tool, based on advanced natural language processing, designed as a digital assistant for educators, enabling the creation of customized lesson plans. The tool utilizes an innovative feature termed 'interactive mega-prompt,' a comprehensive query system that allows educators to input…

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, Tat-Seng Chua
https://arxiv.org/abs/2402.10805

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters. Given a user query for visual content, the MLLM is anticipated to "recall" the relevant image from its parameters as the response. Achieving this target presents notab…

Corpus-Steered Query Expansion with Large Language Models
Yibin Lei, Yu Cao, Tianyi Zhou, Tao Shen, Andrew Yates
https://arxiv.org/abs/2402.18031 https://<…

Corpus-Steered Query Expansion with Large Language Models
Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steer…

CLAPSep: Leveraging Contrastive Pre-trained Models for Multi-Modal Query-Conditioned Target Sound Extraction
Hao Ma, Zhiyuan Peng, Mingjie Shao, Ju Liu, Xu Li, Xixin Wu
https://arxiv.org/abs/2402.17455

CLAPSep: Leveraging Contrastive Pre-trained Models for Multi-Modal Query-Conditioned Target Sound Extraction
Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world sound recordings. Language-queried target sound extraction (TSE) is an effective approach to achieving USS. Such systems consist of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound based on conditional embeddings. Existing methods mainly suffer from two issues: firstly, they require training a randomly initializ…

This https://arxiv.org/abs/2403.13597 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

No more optimization rules: LLM-enabled policy-based multi-modal query optimizer (version 1)
Large language model (LLM) has marked a pivotal moment in the field of machine learning and deep learning. Recently its capability for query planning has been investigated, including both single-modal and multi-modal queries. However, there is no work on the query optimization capability of LLM. As a critical (or could even be the most important) step that significantly impacts the execution performance of the query plan, such analysis and attempts should not be missed. From another aspect, exi…

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, Tat-Seng Chua
https://arxiv.org/abs/2402.10805

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters. Given a user query for visual content, the MLLM is anticipated to "recall" the relevant image from its parameters as the response. Achieving this target presents notab…

Reinforcement Learning from Human Feedback with Active Queries
Kaixuan Ji, Jiafan He, Quanquan Gu
https://arxiv.org/abs/2402.09401 https://

Reinforcement Learning from Human Feedback with Active Queries
Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF approaches often require a large amount of human-labelled preference data, which is expensive to collect. In this paper, inspired by the success of active learning, we address this problem by proposing query-efficient RLHF methods. We first formalize the alignmen…

This https://arxiv.org/abs/2402.04879 has been replaced.
link: https://scholar.google.com/scholar?q=a

Comparing Methods for Creating a National Random Sample of Twitter Users
Twitter data has been widely used by researchers across various social and computer science disciplines. A common aim when working with Twitter data is the construction of a random sample of users from a given country. However, while several methods have been proposed in the literature, their comparative performance is mostly unexplored. In this paper, we implement four common methods to collect a random sample of Twitter users in the US: 1% Stream, Bounding Box, Location Query, and Language Qu…

This https://arxiv.org/abs/2404.19232 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

GRAMMAR: Grounded and Modular Evaluation of Domain-Specific Retrieval-Augmented Language Models
Retrieval-augmented Generation (RAG) systems have been actively studied and deployed across various industries to query on domain-specific knowledge base. However, evaluating these systems presents unique challenges due to the scarcity of domain-specific queries and corresponding ground truths, as well as a lack of systematic approaches to diagnosing the cause of failure cases -- whether they stem from knowledge deficits or issues related to system robustness. To address these challenges, we in…

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models
Atsushi Keyaki, Ribeka Keyaki
https://arxiv.org/abs/2403.16915 https://

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models
Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces coarse-tuning as an intermediate learning stage that bridges pre-training and fine-tuning. By learning query representations and query-document relations in coarse-tuning, we aim to reduce the load of fine-tuning and improve the learning effect of downstream IR t…

This https://arxiv.org/abs/2305.03843 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models
This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during training. We present the first-ever code search method that encodes dynamic runtime information during training without the need to execute either the corpus under search or the search query at inference time and the first code search technique that trains on both p…

This https://arxiv.org/abs/2306.08266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csFL_…

Analyzing Robustness of Angluin's L$^*$ Algorithm in Presence of Noise
Angluin's L$^*$ algorithm learns the minimal deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by numerous random membership queries to get a high level confidence to the answer. Thus it can be applied to any kind of device and may be viewed as an algorithm for synthesizing an automaton abstracting the behavior of the device based on observations. Here we a…

No more optimization rules: LLM-enabled policy-based multi-modal query optimizer (version 1)
Yifan Wang, Haodi Ma, Daisy Zhe Wang
https://arxiv.org/abs/2403.13597

No more optimization rules: LLM-enabled policy-based multi-modal query optimizer (version 1)
Large language model (LLM) has marked a pivotal moment in the field of machine learning and deep learning. Recently its capability for query planning has been investigated, including both single-modal and multi-modal queries. However, there is no work on the query optimization capability of LLM. As a critical (or could even be the most important) step that significantly impacts the execution performance of the query plan, such analysis and attempts should not be missed. From another aspect, exi…

This https://arxiv.org/abs/2403.16915 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models
Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces coarse-tuning as an intermediate learning stage that bridges pre-training and fine-tuning. By learning query representations and query-document relations in coarse-tuning, we aim to reduce the load of fine-tuning and improve the learning effect of downstream IR t…

Efficient Multi-Vector Dense Retrieval Using Bit Vectors
Franco Maria Nardini, Cosimo Rulli, Rossano Venturini
https://arxiv.org/abs/2404.02805 https://

Efficient Multi-Vector Dense Retrieval Using Bit Vectors
Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity measures. In this line, multi-vector representations show improved effectiveness at the expense of a one-order-of-magnitude increase in memory footprint and query latency by encoding queries and documents on a per-token level. Recently, PLAID has tackled these …

This https://arxiv.org/abs/2403.16915 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models
Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces coarse-tuning as an intermediate learning stage that bridges pre-training and fine-tuning. By learning query representations and query-document relations in coarse-tuning, we aim to reduce the load of fine-tuning and improve the learning effect of downstream IR t…

This https://arxiv.org/abs/2305.03843 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models
This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during training. We present the first-ever code search method that encodes dynamic runtime information during training without the need to execute either the corpus under search or the search query at inference time and the first code search technique that trains on both p…

Training Table Question Answering via SQL Query Decomposition
Rapha\"el Mouravieff, Benjamin Piwowarski, Sylvain Lamprier
https://arxiv.org/abs/2402.13288

Training Table Question Answering via SQL Query Decomposition
Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract the relevant information. In this context, many methods have highlighted the benefits of intermediate pre-training from SQL queries. However, while most approaches aim at generating final answers from inputs directly, we claim that there is better to do with SQL queries during training. By learning to imitate a restricted portion of SQL-like algebraic ope…

This https://arxiv.org/abs/2306.08266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csFL_…

Analyzing Robustness of Angluin's L$^*$ Algorithm in Presence of Noise
Angluin's L$^*$ algorithm learns the minimal deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by numerous random membership queries to get a high level confidence to the answer. Thus it can be applied to any kind of device and may be viewed as an algorithm for synthesizing an automaton abstracting the behavior of the device based on observations. Here we a…

This https://arxiv.org/abs/2402.12243 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark
Text-to-SQL, which involves translating natural language into Structured Query Language (SQL), is crucial for enabling broad access to structured databases without expert knowledge. However, designing models for such tasks is challenging due to numerous factors, including the presence of 'noise,' such as ambiguous questions and syntactical errors. This study provides an in-depth analysis of the distribution and types of noise in the widely used BIRD-Bench benchmark and the impact of noise on mo…

This https://arxiv.org/abs/2309.08541 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets
Using large language models (LMs) for query or document expansion can improve generalization in information retrieval. However, it is unknown whether these techniques are universally beneficial or only effective in specific settings, such as for particular retrieval models, dataset domains, or query types. To answer this, we conduct the first comprehensive analysis of LM-based expansion. We find that there exists a strong negative correlation between retriever performance and gains from expansi…

This https://arxiv.org/abs/2310.19056 has been replaced.
link: https://scholar.google.com/scholar?q=a

MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable limitations. Retrieval-based methods often fail to accurately capture search intent, particularly with brief or ambiguous queries. Generation-based methods, utilizing large language models (LLMs), generally lack corpus-specific knowledge and entail high fine-tuni…

Neural Models for Source Code Synthesis and Completion
Mitodru Niyogi
https://arxiv.org/abs/2402.06690 https://arxiv.org/pdf/2402.066…

Neural Models for Source Code Synthesis and Completion
Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems based on semantic parsing. These systems make heavy use of hand-crafted rules that map patterns in NL or elements in its syntax parse tree to various query constructs and can only work on a limited subset of NL with a restricted NL syntax. These systems are …

Fine-tuning Large Language Models with Sequential Instructions
Hanxu Hu, Pinzhen Chen, Edoardo M. Ponti
https://arxiv.org/abs/2403.07794 https://

Fine-tuning Large Language Models with Sequential Instructions
Large language models (LLMs) struggle to follow a sequence of instructions in a single query as they may ignore or misinterpret part of it. This impairs their performance in complex problems whose solution requires multiple intermediate steps, such as multilingual (translate then answer) and multimodal (caption then answer) tasks. We empirically verify this with open-source LLMs as large as LLaMA-2 70B and Mixtral-8x7B. Targeting the scarcity of sequential instructions in present-day data, we p…

QueryExplorer: An Interactive Query Generation Assistant for Search and Exploration
Kaustubh D. Dhole, Shivam Bajaj, Ramraj Chandradevan, Eugene Agichtein
https://arxiv.org/abs/2403.15667

QueryExplorer: An Interactive Query Generation Assistant for Search and Exploration
Formulating effective search queries remains a challenging task, particularly when users lack expertise in a specific domain or are not proficient in the language of the content. Providing example documents of interest might be easier for a user. However, such query-by-example scenarios are prone to concept drift, and the retrieval effectiveness is highly sensitive to the query generation method, without a clear way to incorporate user feedback. To enable exploration and to support Human-In-The…

Fine-tuning Large Language Models with Sequential Instructions
Hanxu Hu, Pinzhen Chen, Edoardo M. Ponti
https://arxiv.org/abs/2403.07794 https://

Fine-tuning Large Language Models with Sequential Instructions
Large language models (LLMs) struggle to follow a sequence of instructions in a single query as they may ignore or misinterpret part of it. This impairs their performance in complex problems whose solution requires multiple intermediate steps, such as multilingual (translate then answer) and multimodal (caption then answer) tasks. We empirically verify this with open-source LLMs as large as LLaMA-2 70B and Mixtral-8x7B. Targeting the scarcity of sequential instructions in present-day data, we p…

Ranked List Truncation for Large Language Model-based Re-Ranking
Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke
https://arxiv.org/abs/2404.18185

Ranked List Truncation for Large Language Model-based Re-Ranking
We study ranked list truncation (RLT) from a novel "retrieve-then-re-rank" perspective, where we optimize re-ranking by truncating the retrieved list (i.e., trim re-ranking candidates). RLT is crucial for re-ranking as it can improve re-ranking efficiency by sending variable-length candidate lists to a re-ranker on a per-query basis. It also has the potential to improve re-ranking effectiveness. Despite its importance, there is limited research into applying RLT methods to this new perspective.…

Generalised Graph Grammars for Natural Language Processing
Oliver Robert Fox, Giacomo Bergami
https://arxiv.org/abs/2403.07481 https://

Generalised Graph Grammars for Natural Language Processing
This seminal paper proposes a new query language for graph matching and rewriting overcoming {the declarative} limitation of Cypher while outperforming {Neo4j} on graph matching and rewriting by at least one order of magnitude. We exploited columnar databases (KnoBAB) to represent graphs using the Generalised Semistructured Model.

This https://arxiv.org/abs/2404.04522 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models
Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively use PEFT for fine-tuning LLMs in ranking tasks with convincing performance; there are some limitations, including the learned prompt being fixed for different documents, overfitting to specific tasks, and low adaptation ability. In this paper, we introduce a qu…

This https://arxiv.org/abs/2311.04694 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Evaluating Generative Ad Hoc Information Retrieval
Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, many generative retrieval systems directly return a grounded generated text as an answer to an information need expressed as a query or question. Quantifying the utility of the textual responses is essential for appropriately evaluating such generative ad hoc retrieval. Yet, the established evaluation methodology for ranking-based retrieval is …

This https://arxiv.org/abs/2306.17563 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researchers have found it difficult to outperform fine-tuned baseline rankers on benchmark datasets. We analyze pointwise and listwise ranking prompts used by existing methods and argue that off-the-shelf LLMs do not fully understand these challenging ranking formulations. In this paper, we propose to significantly reduce th…

Faster Learned Sparse Retrieval with Block-Max Pruning
Antonio Mallia, Torten Suel, Nicola Tonellotto
https://arxiv.org/abs/2405.01117 https://

Faster Learned Sparse Retrieval with Block-Max Pruning
Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by these systems exhibit significant deviations from the ones that use traditional retrieval models, leading to a discrepancy in the performance of existing query optimizations that were specifically developed for traditional structures. These disparities arise from structural variat…

This https://arxiv.org/abs/2310.18376 has been replaced.
link: https://scholar.google.com/scholar?q=a

SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation
In recent years, there has been growing interest in text-to-SQL translation, which is the task of converting natural language questions into executable SQL queries. This technology is important for its potential to democratize data extraction from databases. However, some of its key hurdles include domain generalisation, which is the ability to adapt to previously unseen databases, and alignment of natural language questions with the corresponding SQL queries. To overcome these challenges, we i…

GenSERP: Large Language Models for Whole Page Presentation
Zhenning Zhang, Yunan Zhang, Suyu Ge, Guangwei Weng, Mridu Narang, Xia Song, Saurabh Tiwary
https://arxiv.org/abs/2402.14301

GenSERP: Large Language Models for Whole Page Presentation
The advent of large language models (LLMs) brings an opportunity to minimize the effort in search engine result page (SERP) organization. In this paper, we propose GenSERP, a framework that leverages LLMs with vision in a few-shot setting to dynamically organize intermediate search results, including generated chat answers, website snippets, multimedia data, knowledge panels into a coherent SERP layout based on a user's query. Our approach has three main stages: (1) An information gathering pha…

This https://arxiv.org/abs/2312.15883 has been replaced.
link: https://scholar.google.com/scholar?q=a

HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleten…

Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023
Andrew Parry, Thomas Jaenich, Sean MacAvaney, Iadh Ounis
https://arxiv.org/abs/2405.01122

Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023
This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-shot and pseudo-relevance feedback setting over two sparse retrieval approaches, namely BM25 and SPLADE. We couple this first stage with adaptive re-ranking over a BM25 corpus graph scored using a monoELECTRA cross-encoder. We investigate the efficacy of these generative approaches for different query types in first-st…

Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing
Le Yan, Zhen Qin, Honglei Zhuang, Rolf Jagerman, Xuanhui Wang, Michael Bendersky, Harrie Oosterhuis
https://arxiv.org/abs/2404.11791

Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing
The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as ``How relevant is document A to query Q?", results in sub-optimal ranking. Instead, the pairwise ranking prompting (PRP) approach produces promising ranking performance through asking about pairwise comparisons, e.g., ``Is document A more relevant than document B to query Q?". Thus, while LL…

This https://arxiv.org/abs/2311.06318 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion
Large Language Models (LLMs) excel at tackling various natural language tasks. However, due to the significant costs involved in re-training or fine-tuning them, they remain largely static and difficult to personalize. Nevertheless, a variety of applications could benefit from generations that are tailored to users' preferences, goals, and knowledge. Among them is web search, where knowing what a user is trying to accomplish, what they care about, and what they know can lead to improved search …

This https://arxiv.org/abs/2310.13001 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Conversational Financial Information Retrieval Model (ConFIRM)
With the exponential growth in large language models (LLMs), leveraging their emergent properties for specialized domains like finance merits exploration. However, regulated fields such as finance pose unique constraints, requiring domain-optimized frameworks. We present ConFIRM, an LLM-based conversational financial information retrieval model tailored for query intent classification and knowledge base labeling. ConFIRM comprises two modules: 1) a method to synthesize finance domain-specif…

This https://arxiv.org/abs/2310.13001 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Conversational Financial Information Retrieval Model (ConFIRM)
With the exponential growth in large language models (LLMs), leveraging their emergent properties for specialized domains like finance merits exploration. However, regulated fields such as finance pose unique constraints, requiring domain-optimized frameworks. We present ConFIRM, an LLM-based conversational financial information retrieval model tailored for query intent classification and knowledge base labeling. ConFIRM comprises two modules: 1) a method to synthesize finance domain-specif…

This https://arxiv.org/abs/2010.13442 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Purely Regular Approach to Non-Regular Core Spanners
The regular spanners (characterised by vset-automata) are closed under the algebraic operations of union, join and projection, and have desirable algorithmic properties. The core spanners (introduced by Fagin, Kimelfeld, Reiss, and Vansummeren (PODS 2013, JACM 2015) as a formalisation of the core functionality of the query language AQL used in IBM's SystemT) additionally need string-equality selections and it has been shown by Freydenberger and Holldack (ICDT 2016, Theory of Computing Systems 2…

Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Haoyu Liu, Yaoxian Song, Xuwu Wang, Zhu Xiangru, Zhixu Li, Wei Song, Tiefeng Li
https://arxiv.org/abs/2403.13317

Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
With the explosive growth of multi-modal information on the Internet, unimodal search cannot satisfy the requirement of Internet applications. Text-image retrieval research is needed to realize high-quality and efficient retrieval between different modalities. Existing text-image retrieval research is mostly based on general vision-language datasets (e.g. MS-COCO, Flickr30K), in which the query utterance is rigid and unnatural (i.e. verbosity and formality). To overcome the shortcoming, we cons…

NLQxform-UI: A Natural Language Interface for Querying DBLP Interactively
Ruijie Wang, Zhiruo Zhang, Luca Rossetto, Florian Ruosch, Abraham Bernstein
https://arxiv.org/abs/2403.08475

NLQxform-UI: A Natural Language Interface for Querying DBLP Interactively
In recent years, the DBLP computer science bibliography has been prominently used for searching scholarly information, such as publications, scholars, and venues. However, its current search service lacks the capability to handle complex queries, which limits the usability of DBLP. In this paper, we present NLQxform-UI, a web-based natural language interface that enables users to query DBLP directly with complex natural language questions. NLQxform-UI automatically translates given questions in…

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, Tianyu Du
https://arxiv.org/abs/2403.06840

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if ir…

RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
Zhichao Xu
https://arxiv.org/abs/2403.18276 https://

RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism -- attention requires $O(n^2)$ time complexity in training and $O(n)$ time complexity in inference. Many works have been proposed to improve the attention mechanism's scalability, such as Flash Attention and Multi-query Attention. A different line of work aims t…

RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
Zhichao Xu
https://arxiv.org/abs/2403.18276 https://

RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism -- attention requires $O(n^2)$ time complexity in training and $O(n)$ time complexity in inference. Many works have been proposed to improve the attention mechanism's scalability, such as Flash Attention and Multi-query Attention. A different line of work aims t…

This https://arxiv.org/abs/2402.14301 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

GenSERP: Large Language Models for Whole Page Presentation
The advent of large language models (LLMs) brings an opportunity to minimize the effort in search engine result page (SERP) organization. In this paper, we propose GenSERP, a framework that leverages LLMs with vision in a few-shot setting to dynamically organize intermediate search results, including generated chat answers, website snippets, multimedia data, knowledge panels into a coherent SERP layout based on a user's query. Our approach has three main stages: (1) An information gathering pha…

This https://arxiv.org/abs/2404.04264 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Despite the superb performance in many tasks, large language models (LLMs) bear the risk of generating hallucination or even wrong answers when confronted with tasks that demand the accuracy of knowledge. The issue becomes even more noticeable when addressing logic queries that require multiple logic reasoning steps. On the other hand, knowledge graph (KG) based question answering methods are capable of accurately identifying the correct answers with the help of knowledge graph, yet its accurac…

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
Kunal Sawarkar, Abhilasha Mangal, Shivam Raj Solanki
https://arxiv.org/abs/2404.07220

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q\&A (Question-Answering) systems. However, RAG accuracy becomes increasingly challenging as the corpus of documents scales up, with Retrievers playing an outsized role in the overall RAG accuracy by extracting the most relevant document from the corpus to provide context to the LLM. In this paper, we propose the 'Blended RAG' method o…

Leveraging Translation For Optimal Recall: Tailoring LLM Personalization With User Profiles
Karthik Ravichandran, Sarmistha Sarna Gomasta
https://arxiv.org/abs/2402.13500

Leveraging Translation For Optimal Recall: Tailoring LLM Personalization With User Profiles
This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level translation, semantic embedding-based expansion, and user profile-centered augmentation to address the challenge of matching variance between user queries and relevant documents. Through an initial BM25 retrieval, translation into intermediate languages, embe…

This https://arxiv.org/abs/2404.12237 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

De-DSI: Decentralised Differentiable Search Index
This study introduces De-DSI, a novel framework that fuses large language models (LLMs) with genuine decentralization for information retrieval, particularly employing the differentiable search index (DSI) concept in a decentralized setting. Focused on efficiently connecting novel user queries with document identifiers without direct document access, De-DSI operates solely on query-docid pairs. To enhance scalability, an ensemble of DSI models is introduced, where the dataset is partitioned int…

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
Qi Liu, Gang Guo, Jiaxin Mao, Zhicheng Dou, Ji-Rong Wen, Hao Jiang, Xinyu Zhang, Zhao Cao
https://arxiv.org/abs/2403.13291

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most dense retrieval models using a bi-encoder to encode each query or document into a dense vector, the recently proposed late-interaction multi-vector models (i.e., ColBERT and COIL) achieve state-of-the-art retrieval effectiveness by using all token embeddings to …

De-DSI: Decentralised Differentiable Search Index
Petru Neague, Marcel Gregoriadis, Johan Pouwelse
https://arxiv.org/abs/2404.12237 https://

De-DSI: Decentralised Differentiable Search Index
This study introduces De-DSI, a novel framework that fuses large language models (LLMs) with genuine decentralization for information retrieval, particularly employing the differentiable search index (DSI) concept in a decentralized setting. Focused on efficiently connecting novel user queries with document identifiers without direct document access, De-DSI operates solely on query-docid pairs. To enhance scalability, an ensemble of DSI models is introduced, where the dataset is partitioned int…

This https://arxiv.org/abs/2305.13859 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Generative Retrieval via Term Set Generation
Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for the input query. A common choice for DocID is one or several natural language sequences, e.g. the title or n-grams, so that the pre-trained knowledge of the generative model can be utilized. However, a sequence is generated token by token, where only the most …

Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Andrew Parry, Maik Fr\"obe, Sean MacAvaney, Martin Potthast, Matthias Hagen
https://arxiv.org/abs/2403.07654

Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Modern sequence-to-sequence relevance models like monoT5 can effectively capture complex textual interactions between queries and documents through cross-encoding. However, the use of natural language tokens in prompts, such as Query, Document, and Relevant for monoT5, opens an attack vector for malicious documents to manipulate their relevance score through prompt injection, e.g., by adding target words such as true. Since such possibilities have not yet been considered in retrieval evaluation…

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu, Jian Luan, Bin Wang
https://arxiv.org/abs/2403.06551

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous studies have proposed retrieving suitable tools for the LLM based on the user query. However, previously proposed methods do not consider the differences between seen and unseen tools, nor do they take the hierarchy of the tool library into account, which may le…