Adaptive Triggering for Bias Correction in LLM Reasoning
Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning and create a failure mode that final-answer debiasing alone cannot address. Mitigating such bias during generation presents a fundamental timing problem: intervening too late allows biased reasoning to propagate, while unnecessarily intervening can disrupt otherwise correct reasoning. Existing approaches largely avoid this decision by either evaluating completed reasoning chains post hoc or intervening at predetermined steps, leaving open when a developing reasoning trajectory provides sufficient evidence to warrant correction. We formulate this decision as an online change-point detection problem. A per-step bias signal updates a CUSUM statistic and a targeted correction is injected only when accumulated evidence crosses a detector-specific threshold calibrated on held-out data. We instantiate the framework with a white-box signal derived from next-token probabilities and a black-box signal obtained from an LLM judge, enabling deployment with both open-weight and hosted models. On gpt-4o-mini adaptive black-box triggering recovers most of the disambiguated-context accuracy lost under fixed-interval intervention while requiring substantially fewer interventions. That result holds even with an independent judge. Across six open-weight models, the white-box signal improves ambiguous-item accuracy on all six but reduces disambiguated-item accuracy on five because it cannot distinguish unsupported stereotype reliance from correct, stereotype-congruent evidence.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure hypothesis which posits that early erro…
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it i…
Reinforcement Learning (RL)The Illusion of Insight in Reasoning Models
Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet,…
Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models
Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications…
Reinforcement Learning'Neural howlround' in large language models: a self-reinforcing bias phenomenon, and a dynamic attenuation solution
Large language model (LLM)-driven AI systems may exhibit an inference failure mode we term `neural howlround,' a self-reinforcing cognitive loop where certain highly weighted inputs become dominant, leading to entrenched…
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model