Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback

• URL: http://arxiv.org/abs/2609.17474v1
• Date: Tue, 15 Sep 2026 17:15:40 GMT
• Title: Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
• Abstract summary: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student.<n>Direct imitation, however, can also transfer the teacher's systematic bias and errors.<n>We propose Coupled and Learning (CCL), an algorithm that couples teacher calibration with student updates.
• Score: 24.756084698191568
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can also transfer the teacher's systematic bias and errors. This challenge is particularly pronounced under covariate shift, when the teacher's reliability on target questions is uncertain and target-domain reward feedback is unavailable. We propose Coupled Calibration and Learning (CCL), an LLM distillation algorithm that couples teacher calibration with student updates through token-level branching, using reward feedback only on source questions. Each iteration calibrates the teacher using source feedback and then uses the calibrated teacher to train the student on target questions. The updated student, in turn, informs subsequent calibration. In an autoregressive policy framework, we prove that the output student's expected average Kullback-Leibler divergence to the oracle student converges to zero at a polynomial rate in the number of iterations. The oracle maximizes the true reference-regularized target reward within the student class, which need not represent the unrestricted optimal policy. Our analysis quantifies the progress of projected student gradient updates while controlling the error in teacher calibration. We further establish a separation from regularized direct matching: its error relative to the oracle student can remain bounded away from zero even when the teacher achieves higher regularized target reward than every student policy. These results demonstrate that LLM distillation can overcome persistent teacher bias and recover the optimal student through coupled calibration and learning, without target-domain reward feedback.

Related papers

• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation [49.117085054884676]
  On-policy distillation trains a student model on its own rollouts using dense feedback from a stronger teacher.<n>We operationalize this principle through a trajectory-specific release rule.<n> Experimental results across strong-to-weak distillation tasks indicate that this release rule consistently outperforms standard full-trajectory OPD.
  arXiv  Detail & Related papers  (2026-05-13T15:05:30Z)
• Teacher-Guided Policy Optimization for LLM Distillation [90.49982387646861]
  Teacher-Guided Policy Optimization (TGPO) is an on-policy algorithm that incorporates dense directional guidance by leveraging teacher predictions conditioned on the student's rollout.<n>Experiments on complex reasoning benchmarks demonstrate that TGPO significantly outperforms standard baselines and is robust to different teachers.
  arXiv  Detail & Related papers  (2026-05-13T09:20:03Z)
• OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning [19.98950359294245]
  We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.<n>Despite the performance gains of OPSD, we identify a common but often overlooked mismatch between teacher and student responses.
  arXiv  Detail & Related papers  (2026-05-12T17:00:53Z)
• Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning [2.9029480541171107]
  We propose adaptive teacher exposure as an effective new axis for reasoning self-distillation.<n>We show that Adaptive Teacher Exposure for Self-Distillation (ATESD) consistently outperforms competitive self-distillation and RL baselines.
  arXiv  Detail & Related papers  (2026-05-12T03:15:58Z)
• On-Policy Distillation with Best-of-N Teacher Rollout Selection [54.91780727674628]
  We propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation.<n>BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the teacher trajectory.<n>BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets.
  arXiv  Detail & Related papers  (2026-05-10T19:49:00Z)
• Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning [66.52232008796294]
  Prune-OPD dynamically aligns training budgets with supervision quality.<n>It reduces training time by 37.6%--68.0% while preserving, and often improving, performance on challenging benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T14:38:53Z)
• Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation [14.526961596109361]
  We study statistical estimation in a student--teacher setting, where predictions from a pre-trained teacher are used to guide a student model.<n>A standard approach is to train the student to directly match the teacher's outputs, which we refer to as student soft matching (SM)<n>We propose and analyze an alternative scheme, known as residual-as-teacher (RaT), in which the teacher is used to estimate residuals in the student's predictions.
  arXiv  Detail & Related papers  (2026-03-26T14:07:47Z)
• Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression [27.0471650610245]
  We show that the potential improvement is substantial, in the sense that it affects the scaling law followed by the test error.<n>Strikingly, the student may attain the minimax optimal rate regardless of the scaling law of the teacher.
  arXiv  Detail & Related papers  (2026-03-05T21:32:59Z)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)

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.