How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

Hugging Face Daily Papers Papers
self-distillation financial-reasoning on-policy-training llm-efficiency multi-step-reasoning open-weight-models

Summary

该论文提出 Fin-SD（hindsight self-distillation），一种无需外部教师模型的本地化自蒸馏方法，用于提升小型开放权重模型的多步金融推理能力；实验发现增益主要来自监督位置而非提示内容，且与基于完整参考解答的自蒸馏精度相当但少生成 9.5% token。

Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a strong external teacher, and on-policy self-distillation (OPSD) conditions on a full reference solution. We ask how much of that signal is necessary. We present Fin-SD, a localized hindsight self-distillation recipe for multi-step reasoning. Given a problem the student fails, the student itself identifies the first incorrect reasoning step and writes a short critique of that step. We truncate the student's trajectory immediately before the error (aiming to obtain a correct prefix), condition a frozen copy of the student on the same prefix plus the hint, and distill that hint-conditioned teacher into the student over a short rollout under reverse KL. No external model contributes a gradient. We apply Fin-SD to GPT-OSS-20B on a custom multi-step financial reasoning benchmark that requires deriving formula inputs from realistic scenarios via accounting conventions. We find: (i) replacing the critique with a generic-feedback control matches Fin-SD's entire 3.03 pp accuracy gain over the base model on the FinanceReasoning Hard subset, suggesting the gain comes from where supervision is applied, not hint content; (ii) the model writing the hint does not need to be stronger than the model receiving it: hints from same-family GPT-OSS-120B, at roughly 6x the parameters, yield no materially greater benefits than self-written hints; and (iii) Fin-SD matches on-policy self-distillation from full reference solutions on accuracy while generating 9.5% fewer tokens. With Fin-SD, general reasoning on MMLU-Pro and a fourteen-metric compliance audit on FinTrust show no material regression.
Original Article
View Cached Full Text

Cached at: 10/28/26, 05:28 PM

Paper page - How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

Source: https://huggingface.co/papers/2610.36082

Abstract

Fin-SD improves local multi-step financial reasoning by using self-generated error critiques and truncated correct prefixes for on-policy distillation without external teachers.

Financial institutions operating under data-residency constraints are restricted toopen-weight modelssmall enough to locally host, which trail frontier systems on multi-step quantitative reasoning.On-policy distillationnarrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a strong external teacher, and on-policyself-distillation(OPSD) conditions on a full reference solution. We ask how much of that signal is necessary. We present Fin-SD, a localizedhindsight self-distillationrecipe formulti-step reasoning. Given a problem the student fails, the student itself identifies the first incorrect reasoning step and writes a short critique of that step. We truncate the student’s trajectory immediately before the error (aiming to obtain a correct prefix), condition a frozen copy of the student on the same prefix plus the hint, and distill thathint-conditioned teacherinto the student over a short rollout underreverse KL. No external model contributes a gradient. We apply Fin-SD to GPT-OSS-20B on a custom multi-step financial reasoning benchmark that requires deriving formula inputs from realistic scenarios via accounting conventions. We find: (i) replacing the critique with a generic-feedback control matches Fin-SD’s entire 3.03 pp accuracy gain over the base model on the FinanceReasoning Hard subset, suggesting the gain comes from where supervision is applied, not hint content; (ii) the model writing the hint does not need to be stronger than the model receiving it: hints from same-family GPT-OSS-120B, at roughly 6x the parameters, yield no materially greater benefits than self-written hints; and (iii) Fin-SD matches on-policyself-distillationfrom full reference solutions on accuracy while generating 9.5% fewer tokens. With Fin-SD, general reasoning on MMLU-Pro and a fourteen-metric compliance audit on FinTrust show no material regression.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2610\.36082

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.36082 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.36082 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.36082 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

H^2SD: Hybrid Hindsight Self-Distillation

Hugging Face Daily Papers

Introduces H^2SD, a hybrid hindsight self-distillation framework that improves RLVR by using the teacher model differently for successful and failed trajectories, achieving better reasoning performance.

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Hugging Face Daily Papers

Proposes Anti-Self-Distillation (AntiSD) which reverses the knowledge transfer direction in self-distillation to improve math reasoning efficiency and accuracy, achieving GRPO baseline accuracy in 2-10x fewer steps and up to 11.5 points higher final accuracy across models from 4B to 30B parameters.