# Adaptive Triggering for Bias Correction in LLM Reasoning

arXiv: https://arxiv.org/abs/2608.25379 · HTML: https://mlsanity.com/paper/2608.25379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought](https://mlsanity.com/paper/2403.05518/) (2024)
- [Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs](https://mlsanity.com/paper/2506.07240/) (2025)
- [Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning](https://mlsanity.com/paper/2502.15361/) (2025)
- [Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector](https://mlsanity.com/paper/2505.17100/) (2025)
- [Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow](https://mlsanity.com/paper/2408.08651/) (2024)
- [Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?](https://mlsanity.com/paper/2602.07470/) (2026)
- [Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring](https://mlsanity.com/paper/2603.14251/) (2026)
- [Self-Debias: Self-correcting for Debiasing Large Language Models](https://mlsanity.com/paper/2604.08243/) (2026)
- [Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades](https://mlsanity.com/paper/2604.14251/) (2026)
- [DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model](https://mlsanity.com/paper/2608.05695/) (2026)
- [Sequential statistical inference for Large Language Models: Representation, validity, and monitoring](https://mlsanity.com/paper/2606.07624/) (2026)
- [Reliable Control-Point Selection for Steering Reasoning in Large Language Models](https://mlsanity.com/paper/2604.02113/) (2026)
- [CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning](https://mlsanity.com/paper/2607.20129/) (2026)

## Abstract (arXiv)

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.