{"total":39,"rows":[{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","created":"2021-08-15","cited_by_count":118,"area":"lr"},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112,"area":"lr"},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93,"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":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47,"area":"lr"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2202.12205","title":"Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review","created":"2022-02-24","cited_by_count":38,"area":"lr"},{"id":"2205.12598","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","created":"2022-05-25","cited_by_count":22,"area":"lr"},{"id":"2205.11432","title":"Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models","created":"2022-05-23","cited_by_count":18,"area":"lr"},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"id":"2402.03686","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","created":"2024-02-06","cited_by_count":13,"area":"lr"},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2201.06777","title":"COPA-SSE: Semi-structured Explanations for Commonsense Reasoning","created":"2022-01-18","cited_by_count":8,"area":"lr"},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2604.24401","title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","created":"2026-04-27","cited_by_count":8,"area":"lr"},{"id":"2503.22395","title":"Negation: A Pink Elephant in the Large Language Models' Room?","created":"2025-03-28","cited_by_count":7,"area":"lr"},{"id":"2404.11717","title":"How often are errors in natural language reasoning due to paraphrastic variability?","created":"2024-04-17","cited_by_count":5,"area":"lr"},{"id":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"id":"2306.12552","title":"SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning","created":"2023-06-21","cited_by_count":3,"area":"lr"},{"id":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","cited_by_count":2,"area":"lr"},{"id":"2305.19597","title":"What does the Failure to Reason with \"Respectively\" in Zero/Few-Shot Settings Tell Us about Language Models?","created":"2023-05-31","cited_by_count":2,"area":"lr"},{"id":"2310.18364","title":"From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning","created":"2023-10-24","cited_by_count":2,"area":"lr"},{"id":"2508.10777","title":"The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference","created":"2025-08-14","cited_by_count":2,"area":"lr"},{"id":"2302.08148","title":"Empirical Investigation of Neural Symbolic Reasoning Strategies","created":"2023-02-16","cited_by_count":1,"area":"lr"},{"id":"2311.08637","title":"Formal Proofs as Structured Explanations: Proposing Several Tasks on Explainable Natural Language Inference","created":"2023-11-15","cited_by_count":1,"area":"lr"},{"id":"2504.18376","title":"Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models","created":"2025-04-25","cited_by_count":1,"area":"lr"},{"id":"2603.29025","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2201.04467","title":"How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets","created":"2022-01-12","cited_by_count":0,"area":"lr"},{"id":"2509.10222","title":"Compartmentalised Agentic Reasoning for Clinical NLI","created":"2025-09-12","cited_by_count":0,"area":"lr"},{"id":"2512.20324","title":"Can LLMs Solve My Grandma's Riddle? Evaluating Multilingual Large Language Models on Reasoning Traditional Bangla Tricky Riddles","created":"2025-12-23","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":"2605.27311","title":"Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.26610","title":"Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2610.04915","title":"Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}