{"total":17,"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":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"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":"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":"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":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"id":"2510.07761","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","created":"2025-10-09","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":"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":"2406.14425","title":"SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages","created":"2024-06-20","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":"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":"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}