Hugging Face Trending Papers

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation (OPSD), which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and pushes the student’s distribution away from it. A dynamic gating mechanism isolates reasoning‑critical tokens so that only behavioral flaws are penalized, preserving linguistic capabilities, and empirical results show NSD consistently outperforms OPSD and other label‑free self‑bootstrapping RL baselines.

arXiv Machine Learning
2d ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation, which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and uses a dynamic gating mechanism to target only reasoning‑critical tokens for penalization. This approach preserves foundational language capabilities while consistently outperforming OPSD and other label‑free self‑bootstrapping reinforcement learning baselines.

By Rongcan Pei, Zhepei Wei, Shuyao Xu, Xinyu Zhu, Wei-Lin Chen, Yu Meng
Hugging Face Trending Papers
Jun 17

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.

arXiv AI
Aug 6

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

arXiv:2608. 04794v1 Announce Type: new 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.

By Sarthak Harne, Chinmay Karkar, Yash Pandya, Ahmed Awadallah, Akshay Nambi
arXiv Computer Vision
Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim
arXiv AI
1d ago

Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models

The paper introduces SOLID, a framework that enables operations research language models to self-improve without relying on verified answers or external evaluators. SOLID uses solver-generated artifacts from the model’s own rollouts to create pseudo-references, clustering objectives and applying group-relative advantages for dense self-supervision. Experiments on multiple OR benchmarks show that SOLID enhances solution accuracy for both general-purpose and OR-tuned models compared to outcome-only training.

By Rui Zhu, Minglong Cao, Chenyu Zhou, Jianghao Lin, Dongdong Ge
Hugging Face Trending Papers
Sep 2

Cliff: Learning Process Rewards from the First Mistake

Cliff is a reward‑shaping method for reinforcement learning with verifiable rewards that identifies the first mistake in a language model’s reasoning process using an off‑the‑shelf teacher. It splits each rollout into a correct prefix and an incorrect suffix, assigning positive token‑level advantages to the prefix and negative feedback to the suffix. Across 12 scenarios, Cliff improves reasoning performance, outperforming on‑policy distillation by 15% and standard GRPO by 7%, even with modest teachers.