Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation

• URL: http://arxiv.org/abs/2608.04794v1
• Date: Wed, 05 Aug 2026 12:59:10 GMT
• Title: Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
• Abstract summary: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards.<n>We reproduce SDPO's reported gains in its easy setting, then apply the identical setup to difficult tasks and find that it does not.<n>We explain this failure through a single causal chain from the loss to the model it produces.
• Score: 3.5592415157621105
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it. Reported gains, however, come almost exclusively from narrow, low-difficulty settings, leaving open a basic question: as a lone objective, with no reward term, does SD teach anything? We reproduce SDPO's reported gains in its easy setting, then apply the identical setup to difficult tasks and find that it does not. Across question answering, mathematics, coding, and multi-turn agentic tool use, across reasoning modes, model sizes, and forms of PI, and under both the SDPO and OPSD recipes, the per-token loss falls steadily while validation accuracy does not improve and typically degrades. We explain this failure through a single causal chain from the loss to the model it produces. The chain begins with PI bias: having seen one particular reference solution, the teacher's per-token target is pulled toward that trajectory rather than toward correctness in general, an effect we quantify with a PI Bias Score. Trained to match this target everywhere, the student's objective becomes nearly blind to whether a rollout is correct, and the loss it assigns falls mostly on low-information tokens like stopwords, punctuation, uncertainty markers, rather than those that determine the answer; within correct rollouts the exploratory tokens incur the highest divergence, so it penalizes the hesitation that reasoning requires. The result is a flatter, less decisive student that is no better at reasoning: as a lone objective, SD optimizes a signal decoupled from task success.

Related papers

• Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance [50.77757355236912]
  We propose RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most.<n> Experiments demonstrate that RSTG substantially outperforms naive GRPO+OPD by +4.02% on math and+3.05% on code.
  arXiv  Detail & Related papers  (2026-08-01T17:29:14Z)
• 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)
• DemoPSD: Disagreement-Modulated Policy Self-Distillation [49.30809363804017]
  On-policy self-distillation has emerged as a practical method for training large language models.<n>DemoPSD steers the student toward a weighted geometric combination of the teacher and student distributions.
  arXiv  Detail & Related papers  (2026-07-02T17:58:29Z)
• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning [12.363923974156636]
  Reinforcement learning from verifiable rewards assigns a single scalar to each rollout.<n>On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information.<n>We propose Hindsight Self-Distillation (HSD), which conditions the teacher on a successful peer rollout.
  arXiv  Detail & Related papers  (2026-06-14T03:37:27Z)
• Skill-Conditioned Gated Self-Distillation for LLM Reasoning [22.02868419200851]
  On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision.<n>We propose Skill-Conditioned Gated Self-Distillation (SGSD), which formulates skill-based SD as teacher hypothesis validation rather than unconditional imitation.
  arXiv  Detail & Related papers  (2026-05-27T17:49:52Z)
• CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization [50.59956036193097]
  A model produces a correct solution under reinforcement learning with verifiable rewards (RLVR)<n>Every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler.<n>We propose Contrastive Evidence Policy Optimization (CEPO)<n>CEPO asks a sharper question at every token: "does the correct answer favor this token?" but "does the correct answer favor it while the wrong answer disfavors it?"
  arXiv  Detail & Related papers  (2026-05-19T06:46:19Z)
• Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information [22.436966302243565]
  We propose Anti-Self-Distillation, which ascends a divergence between student and teacher rather than descending it.<n>AntiSD reaches the GRPO baseline's accuracy in 2 to 10x fewer training steps and improves final accuracy by up to 11.5 points.
  arXiv  Detail & Related papers  (2026-05-12T06:40:43Z)
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes [31.95045602299568]
  On-policy distillation (OPD) is appealing for large language model (LLM) post-training because it evaluates teacher feedback on student-generated rollouts rather than fixed teacher traces.<n>We revisit OPD from the estimator and implementation sides.<n>We identify three failure modes of sampled-token OPD: an imbalanced one-token signal, unreliable teacher guidance on student-generated prefixes, and distortions caused by tokenizer or special-token mismatch.
  arXiv  Detail & Related papers  (2026-03-26T15:35:59Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation [25.195244084313114]
  Chain-of-Thought Correctness Perception Distillation (CoPeD) aims to improve the reasoning quality of the student model.<n>CoPeD encourages the student model to predict answers based on correct rationales and revise them when they are incorrect.
  arXiv  Detail & Related papers  (2025-09-06T05:33:17Z)

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.