{"total":100,"rows":[{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168,"area":null},{"id":"2204.07496","title":"Improving Passage Retrieval with Zero-Shot Question Generation","created":"2022-04-15","cited_by_count":165,"area":null},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159,"area":null},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72,"area":null},{"id":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60,"area":null},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2404.03302","title":"How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?","created":"2024-04-04","cited_by_count":44,"area":null},{"id":"2110.06176","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","created":"2021-10-12","cited_by_count":43,"area":null},{"id":"2205.12665","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","created":"2022-05-25","cited_by_count":42,"area":null},{"id":"2310.16570","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2304.04358","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","created":"2023-04-10","cited_by_count":29,"area":null},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2305.15053","title":"Decomposing Complex Queries for Tip-of-the-tongue Retrieval","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2204.00716","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","created":"2022-04-01","cited_by_count":22,"area":null},{"id":"2408.10646","title":"Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs","created":"2024-08-20","cited_by_count":21,"area":null},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","cited_by_count":20,"area":null},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2210.14353","title":"RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering","created":"2022-10-25","cited_by_count":19,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2305.03130","title":"Chain-of-Skills: A Configurable Model for Open-domain Question Answering","created":"2023-05-04","cited_by_count":19,"area":null},{"id":"2402.13492","title":"Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2406.11131","title":"Are Large Language Models a Good Replacement of Taxonomies?","created":"2024-06-17","cited_by_count":19,"area":null},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18,"area":null},{"id":"2305.17080","title":"Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2311.01307","title":"The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models","created":"2023-11-02","cited_by_count":11,"area":null},{"id":"2403.09724","title":"ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2112.05662","title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval","created":"2021-12-10","cited_by_count":10,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2510.09033","title":"Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness","created":"2025-10-10","cited_by_count":10,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2404.11216","title":"Position Engineering: Boosting Large Language Models through Positional Information Manipulation","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2110.01599","title":"Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2205.12680","title":"Optimizing Test-Time Query Representations for Dense Retrieval","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2210.01371","title":"A Study on the Efficiency and Generalization of Light Hybrid Retrievers","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2210.04726","title":"Knowledge Prompts: Injecting World Knowledge into Language Models through Soft Prompts","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2305.17691","title":"Plug-and-Play Knowledge Injection for Pre-trained Language Models","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2212.10381","title":"To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2505.13757","title":"CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2208.05753","title":"Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2210.01959","title":"Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2210.05156","title":"Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2305.14087","title":"BM25 Query Augmentation Learned End-to-End","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2410.15466","title":"Keep Guessing? When Considering Inference Scaling, Mind the Baselines","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2410.19790","title":"Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2502.06252","title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2503.03149","title":"DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2305.11744","title":"ReFIT: Relevance Feedback from a Reranker during Inference","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2402.18264","title":"WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2408.10536","title":"Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.15825","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2509.04011","title":"NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2605.12398","title":"Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.26620","title":"Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2608.20316","title":"Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2205.09638","title":"Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2205.16005","title":"Neural Retriever and Go Beyond: A Thesis Proposal","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2211.04142","title":"Query-Specific Knowledge Graphs for Complex Finance Topics","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2304.05845","title":"Rethinking Dense Retrieval's Few-Shot Ability","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2402.15929","title":"Certifying Knowledge Comprehension in LLMs","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2412.20846","title":"Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2505.23410","title":"From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.21783","title":"Evaluating List Construction and Temporal Understanding capabilities of Large Language Models","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2602.01875","title":"PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2303.05153","title":"Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2405.15028","title":"AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2406.05328","title":"FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2502.19722","title":"Few-Shot Multilingual Open-Domain QA from 5 Examples","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2507.03922","title":"Dynamic Injection of Entity Knowledge into Dense Retrievers","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2508.20778","title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2511.02626","title":"Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2602.17366","title":"RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.00019","title":"The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.21882","title":"Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.09236","title":"Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.23271","title":"Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.02940","title":"When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.22872","title":"Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.29257","title":"Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.24885","title":"The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}