The paper introduces ReDiST, a framework that constructs student‑conditioned reasoning traces to enhance learning beyond answer‑only supervision. ReDiST revises student attempts using evidence and a verified answer, then selects the best traces with a frozen reader that evaluates answer recovery and probability. The distilled student is trained offline, and experiments on QA benchmarks show improved performance over baseline trace methods and highlight varying effectiveness across source and transfer settings.
arXiv:2605. 26872v2 Announce Type: replace-cross Abstract: LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations.
arXiv:2605.26872v4 Announce Type: replace-cross Abstract: LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations....
arXiv:2607. 05734v1 Announce Type: cross Abstract: Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task.
Stepwise-Querying is a method that extracts step-by-step explanations from a black-box teacher model without needing its internal chain-of-thought. By independently querying the teacher for intermediate derivations, validity checks, and corrections for each step, the gathered explanations are used to fine-tune smaller student models. Experiments on mathematics and code benchmarks show that this approach outperforms three baselines in 14 of 16 comparisons, and the introduced Stepwise Explanation Information Gain metric helps diagnose the usefulness of intermediate reasoning.
arXiv:2610.02703v1 Announce Type: new Abstract: On-policy distillation (OPD) improves large language model reasoning by training students on their own rollouts with dense token-wise supervision from...
The paper studies how on‑policy distillation (OPD) can improve answer accuracy while reducing a model’s reliance on supporting evidence. Through matched document interventions, the authors identify an "evidence bypass" phenomenon where a student model keeps an originally correct answer even after the supporting document is changed. They propose Evidence‑Paired OPD (EP‑OPD), which uses matched documents and an answer‑level margin to recover most of the counterfactual accuracy lost by standard OPD while preserving much of its original‑document accuracy gains.
arXiv:2607. 24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model.
COFFEQA introduces a counterfactual-guided few‑shot distillation method for open‑book question answering, leveraging minimally modified contexts that prompt the teacher model to produce alternative answers. By pairing factual samples with validated counterfactuals—filtered using a new Context Following Difficulty metric—COFFEQA constrains the student’s decision boundary to better match the teacher’s. Experiments on multiple QA benchmarks show that COFFEQA consistently outperforms factual‑only distillation, achieving significant gains in EM and F1 scores with a limited few‑shot budget.
arXiv:2602. 01348v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit.
ReTeach is a reflective self‑distillation framework that builds a self‑teacher through multiple rounds of reflection and retry, relying only on self‑generated attempts and outcome‑level verification. Starting from an unsuccessful student rollout, the teacher alternates explicit reflection with new attempts until success or a retry limit is reached, without needing reference answers, external feedback, or cross‑example memory. The method uses outcome‑aware weighting to distinguish correct, reflection‑corrected, and unresolved examples, and on‑policy distillation aligns the student’s token‑level predictions with the teacher’s context‑conditioned distributions, achieving a 1.39‑point accuracy gain over GRPO across six reasoning benchmarks.
TraceForge introduces a two‑stage training method that generates reasoning traces in the style of a target model family, using supervised learning followed by adversarial refinement. The system produces traces that are judged as authentic with scores comparable to real traces, and when applied to teacher answers, it improves performance on coding benchmarks such as HumanEval+ and MBPP+. The approach addresses the limitation of existing models that only return answers without detailed reasoning, enabling more transparent and learnable outputs.
EKLAV is a method that uses a teacher’s chain‑of‑thought (CoT) reasoning as privileged input while supervising only the final answer. By strategically placing parts of the trace in the prompt, EKLAV improves ranking performance on BRIGHT passage reranking and table‑reranking benchmarks, outperforming full‑trace distillation and answer‑only training. The approach reduces training compute and inference time, and the generated traces show more efficient reasoning patterns.