{"total":98,"rows":[{"id":"2506.08837","title":"Design Patterns for Securing LLM Agents against Prompt Injections","created":"2025-06-10","cited_by_count":73,"area":"agents"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2410.03055","title":"Permissive Information-Flow Analysis for Large Language Models","created":"2024-10-04","cited_by_count":22,"area":null},{"id":"2502.09604","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","created":"2025-02-13","cited_by_count":20,"area":"alignment"},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2507.05261","title":"TokenShapley: Token Level Context Attribution with Shapley Value","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2412.15249","title":"LitLLMs, LLMs for Literature Review: Are we there yet?","created":"2024-12-15","cited_by_count":14,"area":null},{"id":"2601.11061","title":"Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs","created":"2026-01-16","cited_by_count":14,"area":"lr"},{"id":"2602.07918","title":"CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution","created":"2026-02-08","cited_by_count":14,"area":"agents"},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2506.01187","title":"LAQuer: Localized Attribution Queries in Content-grounded Generation","created":"2025-06-01","cited_by_count":13,"area":null},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2505.16415","title":"Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation","created":"2025-05-22","cited_by_count":12,"area":"rag"},{"id":"2508.19594","title":"Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs","created":"2025-08-27","cited_by_count":12,"area":"moe"},{"id":"2509.13772","title":"Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation","created":"2025-09-17","cited_by_count":12,"area":"rag"},{"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":"2506.05154","title":"Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement","created":"2025-06-05","cited_by_count":11,"area":"rag"},{"id":"2601.15075","title":"The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution","created":"2026-01-21","cited_by_count":11,"area":"agents"},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2507.04480","title":"Source Attribution in Retrieval-Augmented Generation","created":"2025-07-06","cited_by_count":7,"area":"rag"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2509.13930","title":"Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG","created":"2025-09-17","cited_by_count":7,"area":"rag"},{"id":"2410.03026","title":"Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2604.01194","title":"AgentWatcher: A Rule-based Prompt Injection Monitor","created":"2026-04-01","cited_by_count":6,"area":"safety"},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"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":"2607.21106","title":"AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction","created":"2026-07-23","cited_by_count":5,"area":"agents"},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4,"area":null},{"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":"2505.23183","title":"Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2506.14580","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2607.08011","title":"Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions","created":"2026-07-09","cited_by_count":4,"area":"safety"},{"id":"2412.02626","title":"Time-Reversal Provides Unsupervised Feedback to LLMs","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2512.05958","title":"MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2512.15663","title":"Explaining the Reasoning of Large Language Models Using Attribution Graphs","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2412.04205","title":"A Context-aware Framework for Translation-mediated Conversations","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2504.05317","title":"On Synthesizing Data for Context Attribution in Question Answering","created":"2025-02-21","cited_by_count":2,"area":"synth"},{"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":"2506.19977","title":"Context Attribution with Multi-Armed Bandit Optimization","created":"2025-06-24","cited_by_count":2,"area":"rag"},{"id":"2604.13258","title":"Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2605.06920","title":"In-Context Credit Assignment via the Core","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.07896","title":"What if AI systems weren't chatbots?","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2607.25659","title":"CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2608.26195","title":"Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2504.06138","title":"Multimedia and Visual Analytics in the Agentic Era","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2510.18462","title":"DePass: Unified Feature Attributing by Simple Decomposed Forward Pass","created":"2025-10-21","cited_by_count":1,"area":"mechinterp"},{"id":"2511.15886","title":"What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2512.17179","title":"Enhancing Long Document Long Form Summarisation with Self-Planning","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2604.08438","title":"Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.10862","title":"RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems","created":"2026-05-11","cited_by_count":1,"area":"rag"},{"id":"2606.26449","title":"ProvenAI: Provenance-Native Traces of Evidence in Generated Answers","created":"2026-06-24","cited_by_count":1,"area":"rag"},{"id":"2607.04223","title":"Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)","created":"2026-07-05","cited_by_count":1,"area":"rag"},{"id":"2608.24022","title":"What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.24977","title":"Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation","created":"2026-08-25","cited_by_count":1,"area":"rag"},{"id":"2506.19512","title":"heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation","created":"2025-06-24","cited_by_count":0,"area":"rag"},{"id":"2507.05319","title":"LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2509.04009","title":"Token-Based Detection of Spurious Correlations in Vision Transformers","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.06426","title":"FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.20303","title":"Citation Failure: Definition, Analysis and Efficient Mitigation","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2510.22689","title":"Rule-Based Explanations for Retrieval-Augmented LLM Systems","created":"2025-10-26","cited_by_count":0,"area":"rag"},{"id":"2512.18177","title":"NEURO-GUARD: Neuro-Symbolic Generalization and Unbiased Adaptive Routing for Diagnostics -- Explainable Medical AI","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.21803","title":"Quantifying Retriever-Generator Alignment in RAG with Local Explanations","created":"2026-01-29","cited_by_count":0,"area":"rag"},{"id":"2604.22237","title":"Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.23080","title":"The Attribution Contract for Generative Language Models","created":"2026-05-21","cited_by_count":0,"area":"moe"},{"id":"2606.28358","title":"How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation","created":"2026-06-09","cited_by_count":0,"area":"rag"},{"id":"2606.32008","title":"Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2607.09869","title":"Nonlinear Axiomatic Attribution for Cooperative Games","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.22610","title":"Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations","created":"2026-06-14","cited_by_count":0,"area":"agents"},{"id":"2607.23804","title":"How Context Attribution Handles What the Model Already Knows","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.24651","title":"Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.08284","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.00543","title":"Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation","created":"2026-09-01","cited_by_count":0,"area":"rag"},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.08279","title":"What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.15106","title":"When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.20574","title":"DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30151","title":"Does a model's stated reason for rejecting a candidate do any work?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33405","title":"Decoupling Token Roles in Autoregressive Pretraining","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33676","title":"Auditing Agent Actions through Query-Conditioned Attribution","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34151","title":"Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39473","title":"Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39608","title":"Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02070","title":"Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15883","title":"What the Model Cannot See: Covert and Provable Text Invisibility in LLMs","created":"2026-10-11","cited_by_count":0,"area":"safety"},{"id":"2610.16349","title":"RIFT: Token Influence Follows the Path of Least Resistance","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18389","title":"PRISM: Calibrating Black-Box Judges with Counterfactual Probes","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18427","title":"Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}