{"total":151,"rows":[{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988,"area":"agents"},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312,"area":"rag"},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257,"area":"rag"},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"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":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"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":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2401.08406","title":"RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture","created":"2024-01-16","cited_by_count":81,"area":"rag"},{"id":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71,"area":"rag"},{"id":"2405.06373","title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","created":"2024-05-10","cited_by_count":66,"area":null},{"id":"2312.14183","title":"On Early Detection of Hallucinations in Factual Question Answering","created":"2023-12-19","cited_by_count":56,"area":null},{"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":"2406.14891","title":"Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering","created":"2024-06-21","cited_by_count":51,"area":"rag"},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51,"area":"rag"},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2401.09865","title":"Improving fine-grained understanding in image-text pre-training","created":"2024-01-18","cited_by_count":44,"area":null},{"id":"2310.03184","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","created":"2023-10-04","cited_by_count":38,"area":"rag"},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2406.11811","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","created":"2024-06-17","cited_by_count":26,"area":null},{"id":"2406.15718","title":"Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models","created":"2024-06-22","cited_by_count":26,"area":null},{"id":"2405.13622","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","created":"2024-05-22","cited_by_count":25,"area":"rag"},{"id":"2504.01995","title":"Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics","created":"2025-04-01","cited_by_count":24,"area":"lr"},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2404.12447","title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2403.17848","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","created":"2024-03-26","cited_by_count":20,"area":null},{"id":"2410.04660","title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","created":"2024-10-07","cited_by_count":20,"area":"agents"},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2412.01230","title":"GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering","created":"2024-12-02","cited_by_count":18,"area":"lr"},{"id":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17,"area":"rag"},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2403.07556","title":"Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts","created":"2024-03-12","cited_by_count":15,"area":null},{"id":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"area":null},{"id":"2411.13173","title":"Writing Style Matters: An Examination of Bias and Fairness in Information Retrieval Systems","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2407.06071","title":"From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty","created":"2024-07-08","cited_by_count":14,"area":null},{"id":"2410.01171","title":"Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness","created":"2024-10-02","cited_by_count":14,"area":"rag"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2402.15400","title":"Faithful Temporal Question Answering over Heterogeneous Sources","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2312.08800","title":"Evaluating Large Language Models for Health-related Queries with Presuppositions","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2404.15420","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","created":"2024-04-23","cited_by_count":12,"area":"inference"},{"id":"2410.06304","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2406.06458","title":"Evaluating the Retrieval Component in LLM-Based Question Answering Systems","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2501.08248","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","created":"2025-01-14","cited_by_count":11,"area":"lr"},{"id":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2509.04492","title":"Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2604.16706","title":"Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents","created":"2026-04-17","cited_by_count":10,"area":"agents"},{"id":"2311.09800","title":"$\\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning","created":"2023-11-16","cited_by_count":9,"area":null},{"id":"2403.00827","title":"Self-Refinement of Language Models from External Proxy Metrics Feedback","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2406.18134","title":"Assessing \"Implicit\" Retrieval Robustness of Large Language Models","created":"2024-06-26","cited_by_count":9,"area":"rag"},{"id":"2410.11315","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":9,"area":"rag"},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2502.08356","title":"Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG","created":"2025-02-12","cited_by_count":9,"area":"rag"},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8,"area":"alignment"},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2411.19710","title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","created":"2024-11-29","cited_by_count":8,"area":"rag"},{"id":"2502.18108","title":"Uncertainty Quantification in Retrieval Augmented Question Answering","created":"2025-02-25","cited_by_count":8,"area":"rag"},{"id":"2502.18817","title":"Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models","created":"2025-02-26","cited_by_count":8,"area":"rag"},{"id":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2409.11500","title":"Multi-Document Grounded Multi-Turn Synthetic Dialog Generation","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2504.02867","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","created":"2025-04-01","cited_by_count":7,"area":"agents"},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2311.08390","title":"Predicting Text Preference Via Structured Comparative Reasoning","created":"2023-11-14","cited_by_count":6,"area":"lr"},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2409.11727","title":"Enabling Real-Time Conversations with Minimal Training Costs","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2410.10724","title":"Large Language Models Are Active Critics in NLG Evaluation","created":"2024-10-14","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2506.20844","title":"The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2403.14443","title":"Language Models Can Reduce Asymmetry in Information Markets","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2404.10496","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","created":"2024-04-16","cited_by_count":5,"area":"rag"},{"id":"2501.14733","title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2502.03450","title":"Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System","created":"2025-02-05","cited_by_count":5,"area":"lr"},{"id":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2410.16843","title":"Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning","created":"2024-10-22","cited_by_count":4,"area":"rag"},{"id":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2508.19475","title":"Automatic Question & Answer Generation Using Generative Large Language Model (LLM)","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.04304","title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2509.17445","title":"Semantic Reformulation Entropy for Robust Hallucination Detection in QA Tasks","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2601.16766","title":"Do LLM hallucination detectors suffer from low-resource effect?","created":"2026-01-23","cited_by_count":4,"area":null}],"next_cursor":"100"}