RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.
Gender Bias in LLM-generated Interview Responses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
LLMs have emerged as a promising tool for assisting individuals in diverse text-generation tasks, including job-related texts. However, LLM-generated answers have been increasingly found to exhibit gender bias. This study evaluates three LLMs (GPT-3.5, GPT-4, Claude) to conduct a multifaceted audit of LLM-generated interview responses across models, question types, and jobs, and their alignment with two gender stereotypes. Our findings reveal that gender bias is consistent, and closely aligned with gender stereotypes and the dominance of jobs. Overall, this study contributes to the systematic examination of gender bias in LLM-generated interview responses, highlighting the need for a mindful approach to mitigate such biases in related applications.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Training Large Language Models for Self-Explanation Faithfulness
RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.