{"total":150,"rows":[{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"area":"rag"},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"area":null},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2409.13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","created":"2024-09-10","cited_by_count":137,"area":"agents"},{"id":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"area":null},{"id":"2402.05200","title":"Are LLMs Ready for Real-World Materials Discovery?","created":"2024-02-07","cited_by_count":40,"area":null},{"id":"2502.08554","title":"Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies","created":"2025-02-12","cited_by_count":39,"area":null},{"id":"2505.03970","title":"A Reasoning-Focused Legal Retrieval Benchmark","created":"2025-05-06","cited_by_count":37,"area":"lr"},{"id":"2504.00025","title":"Generalization Bias in Large Language Model Summarization of Scientific Research","created":"2025-03-28","cited_by_count":30,"area":null},{"id":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28,"area":"safety"},{"id":"2504.05559","title":"SciSciGPT: Advancing Human-AI Collaboration in the Science of Science","created":"2025-04-07","cited_by_count":27,"area":null},{"id":"2409.12180","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"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":"2402.02008","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","created":"2024-02-03","cited_by_count":21,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2402.10400","title":"Chain of Logic: Rule-Based Reasoning with Large Language Models","created":"2024-02-16","cited_by_count":18,"area":"lr"},{"id":"2509.00710","title":"On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations","created":"2025-08-31","cited_by_count":18,"area":null},{"id":"2602.05930","title":"Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025","created":"2026-02-05","cited_by_count":15,"area":null},{"id":"2410.02507","title":"Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration","created":"2024-10-03","cited_by_count":14,"area":"lr"},{"id":"2410.07053","title":"Robots in the Middle: Evaluating LLMs in Dispute Resolution","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2506.16335","title":"Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach","created":"2025-06-19","cited_by_count":14,"area":"lr"},{"id":"2502.07912","title":"Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning","created":"2025-02-11","cited_by_count":13,"area":"lr"},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2509.00761","title":"L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit","created":"2025-08-31","cited_by_count":11,"area":"agents"},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"area":null},{"id":"2502.05675","title":"Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning","created":"2025-02-08","cited_by_count":9,"area":"lr"},{"id":"2505.22959","title":"LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements","created":"2025-05-29","cited_by_count":9,"area":"lr"},{"id":"2510.06105","title":"Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2408.03492","title":"Automated Theorem Provers Help Improve Large Language Model Reasoning","created":"2024-08-07","cited_by_count":7,"area":"lr"},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2508.18880","title":"Challenges for Generative AI in Legal Reasoning","created":"2025-08-26","cited_by_count":7,"area":"lr"},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2404.00600","title":"AI Act and Large Language Models (LLMs): When critical issues and privacy impact require human and ethical oversight","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2410.21195","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2501.17830","title":"A Comprehensive Survey on Legal Summarization: Challenges and Future Directions","created":"2025-01-29","cited_by_count":6,"area":null},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","cited_by_count":6,"area":"safety"},{"id":"2505.02164","title":"Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair Use","created":"2025-05-04","cited_by_count":6,"area":"rag"},{"id":"2510.01474","title":"AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2604.03173","title":"Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2407.06798","title":"It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Human","created":"2024-07-09","cited_by_count":5,"area":null},{"id":"2410.09904","title":"Equitable Access to Justice: Logical LLMs Show Promise","created":"2024-10-13","cited_by_count":5,"area":null},{"id":"2601.06216","title":"LLM Agents in Law: Taxonomy, Applications, and Challenges","created":"2026-01-08","cited_by_count":5,"area":"agents"},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5,"area":"rag"},{"id":"2604.16430","title":"HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders","created":"2026-04-06","cited_by_count":5,"area":"mechinterp"},{"id":"2501.13951","title":"A Layered Multi-Expert Framework for Long-Context Mental Health Assessments","created":"2025-01-20","cited_by_count":4,"area":null},{"id":"2503.01688","title":"When an LLM is apprehensive about its answers -- and when its uncertainty is justified","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2507.21110","title":"SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering","created":"2025-07-10","cited_by_count":4,"area":"rag"},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2410.04949","title":"Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.17210","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2412.04576","title":"Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2505.02763","title":"Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2505.18597","title":"LLMs for Supply Chain Management","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2507.12201","title":"RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models","created":"2025-07-16","cited_by_count":3,"area":"diffusion"},{"id":"2508.20040","title":"Model Science: getting serious about verification, explanation and control of AI systems","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2511.06700","title":"Place Matters: Comparing LLM Hallucination Rates for Place-Based Legal Queries","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.16118","title":"Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2407.20248","title":"LAPIS: Language Model-Augmented Police Investigation System","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2505.10792","title":"Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation","created":"2025-05-16","cited_by_count":2,"area":"rag"},{"id":"2510.06002","title":"Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2510.16712","title":"The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2601.14160","title":"Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law","created":"2026-01-20","cited_by_count":2,"area":"synth"},{"id":"2604.13660","title":"VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection","created":"2026-04-15","cited_by_count":2,"area":"lr"},{"id":"2604.22779","title":"KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.21071","title":"Fine-grained Claim-level RAG Benchmark for Law","created":"2026-05-20","cited_by_count":2,"area":"rag"},{"id":"2606.01189","title":"The Case for Model Science: Verify, Explore, Steer, Refine","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2606.19868","title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2606.21155","title":"Who Checks the Citations? Benchmarking Legal Hallucination Detection","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2609.17546","title":"Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2507.10522","title":"DeepResearch$^{\\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology","created":"2025-07-14","cited_by_count":1,"area":"agents"},{"id":"2510.24438","title":"Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content","created":"2025-10-28","cited_by_count":1,"area":"agents"},{"id":"2601.01609","title":"Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration","created":"2026-01-04","cited_by_count":1,"area":"lr"},{"id":"2601.05879","title":"Gender Bias in LLMs: Preliminary Evidence from Shared Parenting Scenario in Czech Family Law","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.15476","title":"Reliability by design: quantifying and eliminating fabrication risk in LLMs. From generative to consultative AI: a comparative analysis in the legal domain and lessons for high-stakes knowledge bases","created":"2026-01-21","cited_by_count":1,"area":"rag"},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.02983","title":"Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2603.04982","title":"Training for Technology: Adoption and Productive Use of Generative AI in Legal Analysis","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.16270","title":"From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2606.00898","title":"Citation Grounding Measures the Oracle: Graph Coverage Determines Reported LLM Hallucination Rates in Law","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.04602","title":"Parthenon Law: A Self-Evolving Legal-Agent Framework","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2606.08932","title":"From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.15646","title":"NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2606.18021","title":"LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI","created":"2026-06-16","cited_by_count":1,"area":"agents"},{"id":"2606.18259","title":"Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2608.16577","title":"BabelSteering: Multilingual Safety Alignment via English Steering Vectors","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2608.20220","title":"InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2610.00609","title":"Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2506.00527","title":"Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning","created":"2025-05-31","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}