Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting
원문 초록
There exist both scalable tasks, like reading comprehension and fact-checking, where model performance improves with model size, and unscalable tasks, like arithmetic reasoning and symbolic reasoning, where model performance does not necessarily improve with model size. Large language models (LLMs) equipped with Chain-of-Thought (CoT) prompting are able to make accurate incremental predictions even on unscalable tasks. Unfortunately, despite their exceptional reasoning abilities, LLMs tend to internalize and reproduce discriminatory societal biases. Whether CoT can provide discriminatory or egalitarian rationalizations for the implicit information in unscalable tasks remains an open question. In this study, we examine the impact of LLMs' step-by-step predictions on gender bias in unscalable tasks. For this purpose, we construct a benchmark for an unscalable task where the LLM is given a list of words comprising feminine, masculine, and gendered occupational words, and is required to count the number of feminine and masculine words. In our CoT prompts, we require the LLM to explicitly indicate whether each word in the word list is a feminine or masculine before making the final predictions. With counting and handling the meaning of words, this benchmark has characteristics of both arithmetic reasoning and symbolic reasoning. Experimental results in English show that without step-by-step prediction, most LLMs make socially biased predictions, despite the task being as simple as counting words. Interestingly, CoT prompting reduces this unconscious social bias in LLMs and encourages fair predictions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification
Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs
Evaluating Large Language Model Capability in Vietnamese Fact-Checking Data Generation
DCR: Quantifying Data Contamination in LLMs Evaluation
DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine
토론
이 논문과 연결된 포럼 글이 아직 없습니다.