{"total":113,"rows":[{"id":"2503.02199","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?","created":"2025-03-04","cited_by_count":89,"area":"mllm"},{"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":"2411.00300","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","created":"2024-11-01","cited_by_count":41,"area":"rag"},{"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":"2501.18636","title":"SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model","created":"2025-01-28","cited_by_count":32,"area":"rag"},{"id":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"area":"rag"},{"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":"2504.18041","title":"RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models","created":"2025-04-25","cited_by_count":24,"area":"rag"},{"id":"2501.07391","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","created":"2025-01-13","cited_by_count":23,"area":"rag"},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","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":"2410.14596","title":"Teaching Models to Balance Resisting and Accepting Persuasion","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2405.03085","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","created":"2024-05-06","cited_by_count":16,"area":"rag"},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2502.18993","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","created":"2025-02-26","cited_by_count":16,"area":"rag"},{"id":"2507.06838","title":"Shifting from Ranking to Set Selection for Retrieval Augmented Generation","created":"2025-07-09","cited_by_count":15,"area":"rag"},{"id":"2605.14473","title":"Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict","created":"2026-05-14","cited_by_count":15,"area":"rag"},{"id":"2408.11875","title":"Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering","created":"2024-08-20","cited_by_count":14,"area":"rag"},{"id":"2410.10360","title":"Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning","created":"2024-10-14","cited_by_count":14,"area":"rag"},{"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":"2411.05059","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2506.11930","title":"Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2410.05162","title":"Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models","created":"2024-10-07","cited_by_count":10,"area":"rag"},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10,"area":"rag"},{"id":"2504.01201","title":"Medical large language models are easily distracted","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2506.20821","title":"MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering","created":"2025-06-25","cited_by_count":9,"area":"rag"},{"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":"2505.22787","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2501.04899","title":"SUGAR: Leveraging Contextual Confidence for Smarter Retrieval","created":"2025-01-09","cited_by_count":7,"area":"rag"},{"id":"2502.17163","title":"MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation","created":"2025-02-24","cited_by_count":7,"area":"rag"},{"id":"2510.21144","title":"NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge","created":"2025-10-24","cited_by_count":7,"area":"rag"},{"id":"2605.17830","title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","created":"2026-05-18","cited_by_count":7,"area":"agents"},{"id":"2601.09760","title":"Investigating Tool-Memory Conflicts in Tool-Augmented LLMs","created":"2026-01-14","cited_by_count":6,"area":"agents"},{"id":"2601.21742","title":"Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems","created":"2026-01-29","cited_by_count":6,"area":"agents"},{"id":"2605.04039","title":"Safety and accuracy follow different scaling laws in clinical large language models","created":"2026-05-05","cited_by_count":6,"area":"lr"},{"id":"2508.19720","title":"Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2409.12468","title":"Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":4,"area":"rag"},{"id":"2504.14856","title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","created":"2025-04-21","cited_by_count":4,"area":"rag"},{"id":"2505.00065","title":"ConSens: Assessing context grounding in open-book question answering","created":"2025-04-30","cited_by_count":4,"area":null},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2510.02370","title":"How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2406.14972","title":"A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems","created":"2024-06-21","cited_by_count":3,"area":"rag"},{"id":"2501.05475","title":"Retrieval-Augmented Generation by Evidence Retroactivity in LLMs","created":"2025-01-07","cited_by_count":3,"area":"lr"},{"id":"2505.09852","title":"Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2506.06240","title":"Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge","created":"2025-06-06","cited_by_count":3,"area":"rag"},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","cited_by_count":3,"area":"synth"},{"id":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2605.26827","title":"ContextGuard: Structured Self-Auditing for Context Learning in Language Models","created":"2026-05-26","cited_by_count":3,"area":"lr"},{"id":"2411.02617","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","created":"2024-11-04","cited_by_count":2,"area":"rag"},{"id":"2502.03916","title":"Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Software","created":"2025-02-06","cited_by_count":2,"area":"rag"},{"id":"2505.13545","title":"Know Or Not: a library for evaluating out-of-knowledge base robustness","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2508.06729","title":"Large Language Models for Oral History Understanding with Text Classification and Sentiment Analysis","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2511.18832","title":"Concept than Document: Context Compression via AMR-based Conceptual Entropy","created":"2025-11-24","cited_by_count":2,"area":"rag"},{"id":"2512.01191","title":"Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2605.12185","title":"Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.22728","title":"When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG","created":"2026-06-22","cited_by_count":2,"area":"rag"},{"id":"2607.12650","title":"Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2607.26843","title":"When Knowledge Changes: Metamorphic Testing of RAG Systems with Mutations","created":"2026-07-29","cited_by_count":2,"area":"rag"},{"id":"2509.25184","title":"Incentive-Aligned Multi-Source LLM Summaries","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2511.10881","title":"A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2602.04918","title":"Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.14518","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"id":"2603.25960","title":"When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models","created":"2026-03-26","cited_by_count":1,"area":"lr"},{"id":"2604.22335","title":"Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding","created":"2026-04-24","cited_by_count":1,"area":"safety"},{"id":"2604.25313","title":"Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.18792","title":"Trust or Abstain? A Self-Aware RAG Approach","created":"2026-05-11","cited_by_count":1,"area":"rag"},{"id":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.10298","title":"From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.22419","title":"Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering","created":"2026-06-21","cited_by_count":1,"area":"rag"},{"id":"2606.25476","title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2606.29894","title":"SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2607.03739","title":"A Failure-Mode Benchmark for Polymorphic Sybil Poisoning in RAG","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.19355","title":"Information Discernment in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2609.05587","title":"Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.30087","title":"Return or Revise? Learning When Revision Helps Retrieval-Augmented QA","created":"2026-09-24","cited_by_count":1,"area":"rag"},{"id":"2409.06518","title":"Medal Matters: Probing LLMs' Failure Cases Through Olympic Rankings","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2411.06207","title":"KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models","created":"2024-11-09","cited_by_count":0,"area":null},{"id":"2412.06303","title":"DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2501.01332","title":"Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2508.01084","title":"Provably Secure Retrieval-Augmented Generation","created":"2025-08-01","cited_by_count":0,"area":"rag"},{"id":"2508.02074","title":"The SMeL Test: A simple benchmark for media literacy in language models","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.05179","title":"ATLANTIS at SemEval-2025 Task 3: Detecting Hallucinated Text Spans in Question Answering","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.06902","title":"Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2511.05498","title":"Biomedical Hypothesis Explainability with Graph-Based Context Retrieval","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2601.05260","title":"Quantifying Document Impact in RAG-LLMs","created":"2025-10-27","cited_by_count":0,"area":"rag"},{"id":"2603.16581","title":"V-DyKnow: A Dynamic Benchmark for Time-Sensitive Knowledge in Vision Language Models","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2604.22193","title":"How Large Language Models Balance Internal Knowledge with User and Document Assertions","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.06919","title":"Can LLMs Take Retrieved Information with a Grain of Salt?","created":"2026-05-07","cited_by_count":0,"area":"rag"},{"id":"2605.26019","title":"Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service","created":"2026-05-25","cited_by_count":0,"area":"rag"},{"id":"2606.11208","title":"BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.18673","title":"MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.24117","title":"Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.25953","title":"Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.28421","title":"When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":"100"}