{"total":62,"rows":[{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2304.10703","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","created":"2023-04-21","cited_by_count":77,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2410.17245","title":"Towards Reliable Evaluation of Behavior Steering Interventions in LLMs","created":"2024-10-22","cited_by_count":36,"area":"mechinterp"},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35,"area":null},{"id":"2203.06204","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","created":"2022-03-11","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2205.07043","title":"Naturalistic Causal Probing for Morpho-Syntax","created":"2022-05-14","cited_by_count":19,"area":null},{"id":"2408.13678","title":"A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models","created":"2024-08-24","cited_by_count":18,"area":null},{"id":"2502.00577","title":"Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach","created":"2025-02-01","cited_by_count":16,"area":"mllm"},{"id":"2406.00053","title":"Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting","created":"2024-05-28","cited_by_count":15,"area":null},{"id":"2204.06201","title":"Probing for Constituency Structure in Neural Language Models","created":"2022-04-13","cited_by_count":14,"area":null},{"id":"2306.08193","title":"Operationalising Representation in Natural Language Processing","created":"2023-06-14","cited_by_count":14,"area":null},{"id":"2410.11627","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","created":"2024-10-15","cited_by_count":14,"area":null},{"id":"2405.16702","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2305.18213","title":"Gaussian Process Probes (GPP) for Uncertainty-Aware Probing","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2303.03951","title":"Probing Graph Representations","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9,"area":"lr"},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2203.09306","title":"Finding Structural Knowledge in Multimodal-BERT","created":"2022-03-17","cited_by_count":7,"area":null},{"id":"2206.01512","title":"Latent Topology Induction for Understanding Contextualized Representations","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2504.08001","title":"Linguistic Interpretability of Transformer-based Language Models: a systematic review","created":"2025-04-09","cited_by_count":7,"area":"mechinterp"},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2208.12352","title":"OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2310.17936","title":"Transformers as Graph-to-Graph Models","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2407.01384","title":"Free-text Rationale Generation under Readability Level Control","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2505.01958","title":"A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models","created":"2025-05-04","cited_by_count":4,"area":"mllm"},{"id":"2310.17284","title":"Learning to Abstract with Nonparametric Variational Information Bottleneck","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2510.18914","title":"Fairness Evaluation and Inference Level Mitigation in LLMs","created":"2025-10-21","cited_by_count":2,"area":"safety"},{"id":"2605.06723","title":"When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.01092","title":"A Fiber Criterion for Representation Identifiability in Supervised Learning","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2210.06928","title":"Sentence Ambiguity, Grammaticality and Complexity Probes","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2301.11688","title":"Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?","created":"2023-01-27","cited_by_count":1,"area":"distill"},{"id":"2310.04557","title":"Measuring Information in Text Explanations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2312.15359","title":"TVE: Learning Meta-attribution for Transferable Vision Explainer","created":"2023-12-23","cited_by_count":1,"area":null},{"id":"2403.13106","title":"Using Shapley interactions to understand how models use structure","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2511.07577","title":"A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain","created":"2025-11-10","cited_by_count":1,"area":"rag"},{"id":"2512.17270","title":"Understanding Generalization in Role-Playing Models via Information Theory","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2605.25310","title":"Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2310.11363","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2310.12454","title":"Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models","created":"2023-10-19","cited_by_count":0,"area":"lr"},{"id":"2506.21861","title":"Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2603.23433","title":"Mecha-nudges for Machines","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.00607","title":"Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2608.15772","title":"Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.17843","title":"Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.27813","title":"Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.08618","title":"Target-Independent Micro-Interventions for Predicting Training Response Across Language-Model Families","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.32889","title":"Measurement-Gated Provenance Attenuation for Frozen EEG Representations","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36534","title":"Retrieval Sensitivity to Identity Signals in Queries","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38956","title":"Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01495","title":"Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.19373","title":"Evaluating Compressed Memory: Dependence, Utility, and Content Benefit","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}