{"total":16,"rows":[{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2402.11398","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","created":"2024-02-17","cited_by_count":21,"area":"lr"},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17,"area":"lr"},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2209.02552","title":"From Black Boxes to Conversations: Incorporating XAI in a Conversational Agent","created":"2022-09-06","cited_by_count":14,"area":"lr"},{"id":"2505.00875","title":"Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines","created":"2025-05-01","cited_by_count":7,"area":"lr"},{"id":"2209.13710","title":"Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge","created":"2022-09-27","cited_by_count":6,"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":"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":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2308.02950","title":"A criterion for Artificial General Intelligence: hypothetic-deductive reasoning, tested on ChatGPT","created":"2023-08-05","cited_by_count":1,"area":"lr"},{"id":"2603.07306","title":"Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks","created":"2026-03-07","cited_by_count":1,"area":"lr"},{"id":"2507.04893","title":"MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction","created":"2025-07-07","cited_by_count":0,"area":"lr"},{"id":"2604.08140","title":"Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2605.14845","title":"Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2607.14756","title":"AI vs Human Expert Reasoning: Assessing Agreements in Building Typology Predictions based on Street View Imagery","created":"2026-07-16","cited_by_count":0,"area":"lr"}],"next_cursor":null}