{"total":356,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128,"area":"rag"},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369,"area":"rag"},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341,"area":null},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327,"area":null},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287,"area":null},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283,"area":"rag"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174,"area":null},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169,"area":null},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131,"area":null},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2404.10198","title":"ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence","created":"2024-04-16","cited_by_count":113,"area":"rag"},{"id":"2311.13230","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","created":"2023-11-22","cited_by_count":99,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96,"area":null},{"id":"2402.14409","title":"Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models","created":"2024-02-22","cited_by_count":93,"area":"rag"},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91,"area":null},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80,"area":null},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2402.11782","title":"What Evidence Do Language Models Find Convincing?","created":"2024-02-19","cited_by_count":75,"area":"rag"},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2410.15999","title":"Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering","created":"2024-10-21","cited_by_count":63,"area":"mechinterp"},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"rag"},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56,"area":null},{"id":"2305.01579","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","created":"2023-05-02","cited_by_count":54,"area":"rag"},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2405.02750","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","created":"2024-05-04","cited_by_count":49,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2406.13805","title":"WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia","created":"2024-06-19","cited_by_count":44,"area":"rag"},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2305.15076","title":"Meta-Learning Online Adaptation of Language Models","created":"2023-05-24","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":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2112.08688","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","created":"2021-12-16","cited_by_count":40,"area":"rag"},{"id":"2112.08634","title":"FRUIT: Faithfully Reflecting Updated Information in Text","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2406.18406","title":"IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons","created":"2024-06-26","cited_by_count":38,"area":null},{"id":"2410.08145","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","created":"2024-10-10","cited_by_count":38,"area":"mllm"},{"id":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2409.07394","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","created":"2024-09-11","cited_by_count":37,"area":null},{"id":"2310.14393","title":"Merging Generated and Retrieved Knowledge for Open-Domain QA","created":"2023-10-22","cited_by_count":36,"area":null},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2310.14820","title":"ALCUNA: Large Language Models Meet New Knowledge","created":"2023-10-23","cited_by_count":35,"area":null},{"id":"2403.04317","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35,"area":null},{"id":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35,"area":null},{"id":"2407.17023","title":"DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models","created":"2024-07-24","cited_by_count":34,"area":null},{"id":"2410.13509","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","created":"2024-10-17","cited_by_count":33,"area":"rag"},{"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":"2503.10996","title":"Taming Knowledge Conflicts in Language Models","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2310.12516","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","created":"2023-10-19","cited_by_count":28,"area":"rag"},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28,"area":null},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28,"area":"mllm"},{"id":"2506.08938","title":"FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation","created":"2025-06-10","cited_by_count":28,"area":"rag"},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2402.11893","title":"Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2404.16032","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","created":"2024-04-24","cited_by_count":27,"area":"rag"},{"id":"2404.04633","title":"Context versus Prior Knowledge in Language Models","created":"2024-04-06","cited_by_count":26,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2410.14675","title":"To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts","created":"2024-10-18","cited_by_count":25,"area":"rag"},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25,"area":null},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24,"area":null},{"id":"2309.17415","title":"Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts","created":"2023-09-29","cited_by_count":23,"area":"rag"},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2403.19216","title":"Are Large Language Models Good at Utility Judgments?","created":"2024-03-28","cited_by_count":22,"area":"rag"},{"id":"2305.14695","title":"A Causal View of Entity Bias in (Large) Language Models","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2407.03993","title":"A Survey on Natural Language Counterfactual Generation","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2410.15737","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","created":"2024-10-21","cited_by_count":21,"area":"rag"},{"id":"2502.11367","title":"Sparse Autoencoder Features for Classifications and Transferability","created":"2025-02-17","cited_by_count":21,"area":"mechinterp"},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20,"area":null},{"id":"2408.03297","title":"KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models","created":"2024-08-06","cited_by_count":20,"area":"rag"},{"id":"2302.09170","title":"KILM: Knowledge Injection into Encoder-Decoder Language Models","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19,"area":"agents"},{"id":"2406.17519","title":"Entropy-Based Decoding for Retrieval-Augmented Large Language Models","created":"2024-06-25","cited_by_count":19,"area":"rag"},{"id":"2408.01084","title":"Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts","created":"2024-08-02","cited_by_count":19,"area":"rag"}],"next_cursor":"100"}