{"total":19,"rows":[{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199,"area":"lr"},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2404.03134","title":"Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?","created":"2024-04-04","cited_by_count":17,"area":"lr"},{"id":"2310.14607","title":"Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications","created":"2023-10-23","cited_by_count":15,"area":"lr"},{"id":"2306.01117","title":"Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning","created":"2023-06-01","cited_by_count":8,"area":"lr"},{"id":"2412.15375","title":"Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluation","created":"2024-12-19","cited_by_count":5,"area":"lr"},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2505.17217","title":"Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2510.12818","title":"MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2503.00355","title":"Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data","created":"2025-03-01","cited_by_count":2,"area":"lr"},{"id":"2602.04742","title":"Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2508.04939","title":"I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2511.06160","title":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2511.06023","title":"Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data","created":"2025-11-08","cited_by_count":0,"area":"lr"},{"id":"2605.02348","title":"Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2605.30214","title":"GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.16562","title":"MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2609.19006","title":"WordPolo: Evaluating Language Models Through Iterative Semantic Feedback","created":"2026-07-18","cited_by_count":0,"area":"lr"}],"next_cursor":null}