Adaptive Triggering for Bias Correction in LLM Reasoning

• URL: http://arxiv.org/abs/2608.25379v1
• Date: Wed, 26 Aug 2026 05:08:35 GMT
• Title: Adaptive Triggering for Bias Correction in LLM Reasoning
• Abstract summary: Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning.<n>We formulate this decision as an online change-point detection problem.<n>We instantiate the framework with a white-box signal derived from next-token probabilities and a black-box signal obtained from an LLM judge.
• Score: 11.48742254002371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation [14.844162865265673]
  We propose CARD, which maps the temporal aggregate of disagreement to a temperature field applied per pixel across all classes, so that confidence changes while the segmentation does not.<n>Across cardiac, prostate and brain MRI shifts, CARD lowers calibration error in 45 of 49 comparisons against the strongest baseline in each setting.
  arXiv  Detail & Related papers  (2026-08-26T07:23:08Z)
• Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models [7.714704554667688]
  Large Language Models (LLMs) increasingly support decision-making in high-stakes domains.<n>LLMs often hallucinate and express confidence that is misaligned with factual correctness.<n>We study claim-level confidence calibration as a decision-relevant uncertainty signal.
  arXiv  Detail & Related papers  (2026-08-23T16:09:54Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs? [53.58941416780391]
  We study where this susceptibility, spanning sycophancy and related cue-induced biases, lives inside the model.<n>We extract a per-bias direction from hidden states and triangulate it through three measures: probing, leave-one-dataset-out transfer, and causal intervention.
  arXiv  Detail & Related papers  (2026-07-20T16:10:06Z)
• Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation [0.0]
  Large autoregressive language models exhibit a self-correction blind spot.<n>We prove a spectral-algebraic theory of self-correction in autoregressive generation.
  arXiv  Detail & Related papers  (2026-07-09T17:52:16Z)
• Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM Reasoning [5.634990956257954]
  Large language models produce fluent but often incorrect multi-step reasoning, and naive correction methods risk degrading already-correct answers.<n>We introduce Denoising Iterative Self-Correction (DISC), a test-time procedure that treats verification question outputs as noisy measurements of where a solution may be corrupted.<n>A binary judgment gate controls correction precision by blocking rewrites that would damage already-correct answers while the verifier and corrector together repair errors.
  arXiv  Detail & Related papers  (2026-06-19T20:23:14Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning [32.32593439144886]
  Behavior-calibrated reinforcement learning allows smaller models to surpass frontier models in uncertainty quantification.<n>Our model's log-scale Accuracy-to-Hallucination Ratio gain (0.806) exceeds GPT-5's (0.207) in a challenging in-domain evaluation.
  arXiv  Detail & Related papers  (2025-12-22T22:51:48Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation [139.4332115349543]
  Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. How to estimate the predictive uncertainty of DA models is vital for decision-making in safety-critical scenarios. TransCal can be easily applied to recalibrate existing DA methods.
  arXiv  Detail & Related papers  (2020-07-16T11:09:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.