{"total":92,"rows":[{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"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":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2311.07230","title":"How are Prompts Different in Terms of Sensitivity?","created":"2023-11-13","cited_by_count":35,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2307.13339","title":"Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions","created":"2023-07-25","cited_by_count":32,"area":"lr"},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2501.17546","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","created":"2025-01-29","cited_by_count":26,"area":null},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2410.06496","title":"On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task","created":"2024-10-09","cited_by_count":24,"area":null},{"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":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2502.09723","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","created":"2025-02-13","cited_by_count":18,"area":"alignment"},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2502.20344","title":"LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2305.07378","title":"Surfacing Biases in Large Language Models using Contrastive Input Decoding","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2310.11906","title":"Rather a Nurse than a Physician -- Contrastive Explanations under Investigation","created":"2023-10-18","cited_by_count":11,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","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":"2504.00597","title":"On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation","created":"2025-04-01","cited_by_count":10,"area":"rag"},{"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":"2405.20434","title":"Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2310.01188","title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2404.07498","title":"Interactive Prompt Debugging with Sequence Salience","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2501.13115","title":"Dagger Behind Smile: Fool LLMs with a Happy Ending Story","created":"2025-01-19","cited_by_count":6,"area":"safety"},{"id":"2507.18043","title":"GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs","created":"2025-07-24","cited_by_count":6,"area":"mllm"},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2404.01361","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2411.02643","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2209.01174","title":"Extend and Explain: Interpreting Very Long Language Models","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2311.13061","title":"Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2312.06499","title":"TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2411.16252","title":"NormXLogit: The Head-on-Top Never Lies","created":"2024-11-25","cited_by_count":4,"area":null},{"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":"2510.05025","title":"Imperceptible Jailbreaking against Large Language Models","created":"2025-10-06","cited_by_count":4,"area":"safety"},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2403.02558","title":"The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN)","created":"2024-03-05","cited_by_count":3,"area":"mllm"},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2505.01557","title":"Contextures: Representations from Contexts","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2509.26543","title":"The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models","created":"2025-09-30","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":"2604.18389","title":"Understanding the Prompt Sensitivity","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2410.18541","title":"On Explaining with Attention Matrices","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2412.04205","title":"A Context-aware Framework for Translation-mediated Conversations","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2512.08440","title":"What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2602.18160","title":"Unifying Formal Explanations: A Complexity-Theoretic Perspective","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2310.04557","title":"Measuring Information in Text Explanations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2408.01969","title":"Optimal and efficient text counterfactuals using Graph Neural Networks","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2503.16444","title":"Conversational Explanations: Discussing Explainable AI with Non-AI Experts","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2509.02075","title":"How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2305.18915","title":"Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures","created":"2023-05-30","cited_by_count":0,"area":"synth"},{"id":"2310.04856","title":"LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2402.05581","title":"Establishing degrees of closeness between audio recordings along different dimensions using large-scale cross-lingual models","created":"2024-02-08","cited_by_count":0,"area":null},{"id":"2406.11785","title":"CELL your Model: Contrastive Explanations for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2407.02136","title":"Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2408.11554","title":"Differentiating Choices via Commonality for Multiple-Choice Question Answering","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2503.01914","title":"Conceptual Contrastive Edits in Textual and Vision-Language Retrieval","created":"2025-03-01","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":"2511.21086","title":"Orthographic Constraint Satisfaction and Human Difficulty Alignment in Large Language Models","created":"2025-11-26","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":"2605.23080","title":"The Attribution Contract for Generative Language Models","created":"2026-05-21","cited_by_count":0,"area":"moe"},{"id":"2606.09466","title":"DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.22546","title":"Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attribution","created":"2026-05-06","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":"2608.02879","title":"Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.10434","title":"Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.28117","title":"Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation","created":"2026-09-23","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":"2609.33676","title":"Auditing Agent Actions through Query-Conditioned Attribution","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.05277","title":"Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}