{"total":54,"rows":[{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39,"area":"lr"},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"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":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2502.00330","title":"From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation","created":"2025-02-01","cited_by_count":21,"area":"lr"},{"id":"2601.07408","title":"Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning","created":"2026-01-12","cited_by_count":19,"area":"lr"},{"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":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2305.10496","title":"Incorporating Attribution Importance for Improving Faithfulness Metrics","created":"2023-05-17","cited_by_count":14,"area":"lr"},{"id":"2402.11900","title":"Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models","created":"2024-02-19","cited_by_count":14,"area":"lr"},{"id":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14,"area":"lr"},{"id":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2206.04928","title":"GAMR: A Guided Attention Model for (visual) Reasoning","created":"2022-06-10","cited_by_count":12,"area":"lr"},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"id":"2505.08392","title":"Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning","created":"2025-05-13","cited_by_count":12,"area":"lr"},{"id":"2310.05797","title":"In-Context Explainers: Harnessing LLMs for Explaining Black Box Models","created":"2023-10-09","cited_by_count":9,"area":"lr"},{"id":"2409.14759","title":"VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2302.12569","title":"Implicit Temporal Reasoning for Evidence-Based Fact-Checking","created":"2023-02-24","cited_by_count":7,"area":"lr"},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2508.12140","title":"Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality","created":"2025-08-16","cited_by_count":6,"area":"lr"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2212.09282","title":"APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning","created":"2022-12-19","cited_by_count":5,"area":"lr"},{"id":"2504.05908","title":"PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario","created":"2025-04-08","cited_by_count":3,"area":"lr"},{"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":"2603.03475","title":"When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2307.12382","title":"CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models","created":"2023-07-23","cited_by_count":2,"area":"lr"},{"id":"2402.06120","title":"Exploring Group and Symmetry Principles in Large Language Models","created":"2024-02-09","cited_by_count":2,"area":"lr"},{"id":"2412.15748","title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","created":"2024-12-20","cited_by_count":2,"area":"lr"},{"id":"2603.03335","title":"Compressed Sensing for Capability Localization in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2606.04889","title":"GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2402.12675","title":"Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach","created":"2024-02-20","cited_by_count":1,"area":"lr"},{"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":"2601.11666","title":"MATEX: Multi-scale Attention and Text-guided Explainability of Medical Vision-Language Models","created":"2026-01-16","cited_by_count":1,"area":"lr"},{"id":"2602.15332","title":"Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2604.18307","title":"Reasoning Models Know What's Important, and Encode It in Their Activations","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.11906","title":"YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2510.08613","title":"GraphGhost: Tracing Structures Behind Large Language Models","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2601.11625","title":"Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2602.14002","title":"The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2605.02962","title":"ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2605.11404","title":"Attributing Emergence in Million-Agent Systems","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.29951","title":"MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.09030","title":"TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2608.08224","title":"Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.04194","title":"Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.24243","title":"Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.27041","title":"Math Reasoning in LLMs is Organized by Approach, Not Topic","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33851","title":"Rethinking Contextualization by Reinterpreting Attention Head Channels","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}