{"total":41,"rows":[{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"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":"2406.06579","title":"From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks","created":"2024-06-04","cited_by_count":38,"area":"lr"},{"id":"2501.15674","title":"TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs","created":"2025-01-26","cited_by_count":12,"area":"lr"},{"id":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11,"area":"lr"},{"id":"2310.06374","title":"Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models","created":"2023-10-10","cited_by_count":8,"area":"lr"},{"id":"2602.15580","title":"How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning","created":"2026-02-17","cited_by_count":8,"area":"lr"},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"id":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","cited_by_count":7,"area":"lr"},{"id":"2510.13903","title":"Benefits and Limitations of Communication in Multi-Agent Reasoning","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2501.12997","title":"Ehrenfeucht-Haussler Rank and Chain of Thought","created":"2025-01-22","cited_by_count":6,"area":"lr"},{"id":"2204.05673","title":"What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured","created":"2022-04-12","cited_by_count":5,"area":"lr"},{"id":"2311.08614","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","created":"2023-11-15","cited_by_count":5,"area":"lr"},{"id":"2503.09820","title":"ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation","created":"2025-03-12","cited_by_count":5,"area":"lr"},{"id":"2505.22137","title":"Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2512.10978","title":"Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2205.13183","title":"Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach","created":"2022-05-26","cited_by_count":4,"area":"lr"},{"id":"2307.01784","title":"The Inner Sentiments of a Thought","created":"2023-07-04","cited_by_count":4,"area":"lr"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2607.00924","title":"Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2201.01787","title":"Does Entity Abstraction Help Generative Transformers Reason?","created":"2022-01-05","cited_by_count":3,"area":"lr"},{"id":"2403.14932","title":"Extending Token Computation for LLM Reasoning","created":"2024-03-22","cited_by_count":3,"area":"lr"},{"id":"2509.20336","title":"Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing","created":"2025-09-24","cited_by_count":3,"area":"lr"},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","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":"2410.21353","title":"Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics","created":"2024-10-28","cited_by_count":1,"area":"lr"},{"id":"2507.00092","title":"Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models","created":"2025-06-30","cited_by_count":1,"area":"lr"},{"id":"2508.06084","title":"AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance","created":"2025-08-08","cited_by_count":1,"area":"lr"},{"id":"2603.09205","title":"Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing","created":"2026-03-10","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":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2608.17950","title":"Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.23518","title":"Investigating Relational Reasoning in VLMs","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","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":"2610.18127","title":"Monitoring latent reasoning in looped language models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}