← Back to all news
arXiv AI By Yecheng Wu, Song Han, Han Cai

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

Read the original on arXiv AI →

The paper introduces Weakening-Induced On-Policy Self-Distillation (WISD), a method that improves large reasoning models by creating a weaker version of the original model and using the contrast between them as a training signal, without needing privileged information. WISD constructs the weaker model via low-bit quantization or magnitude pruning, and evaluates it on mathematical and coding reasoning tasks across various architectures and scales. The results show significant accuracy gains—up to 5.5 percentage points—over the original models, achieving state‑of‑the‑art performance on benchmarks such as HMMT 2025 and LiveCodeBench v6.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 30

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.

By Xiaojun Wu, Xiaoguang Jiang, Huiyang Li, Jucai Zhai, Dengfeng Liu, Qiaobo Hao, Huang Liu, Zhiguo Yang, Ji Xie, Ninglun Gu, Jin Yang, Kailai Zhang, Yelun Bao, Jun Wang
llmsreinforcement-learningfine-tuningefficiencybenchmarks
More like this →
arXiv AI
Oct 2

Masked Self-Distillation: Internalizing the Chain-of-Thought in Language Models

The paper introduces masked self‑distillation, a post‑training framework that trains a language model to internalize portions of its own intermediate reasoning traces. By varying the fraction of trace internalized, the authors demonstrate that models can achieve higher inference efficiency and improved task performance on math and graph‑coloring problems. Experiments on Qwen3‑4B and Qwen3‑8B show that the method generalizes well to in‑domain out‑of‑distribution cases without catastrophic forgetting, and that supervised fine‑tuning alone can reduce trace length at the expense of generalization.

By Durgesh Kalwar, Vardhan Palod, Jaya Adithya Pavuluri, Subbarao Kambhampati
llmsfine-tuningefficiencybenchmarks
More like this →
arXiv AI
5d ago

ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning

ThinkBit is a two‑bit scalar quantization framework designed to preserve reasoning capabilities in language models. It assigns each layer a ternary, 2‑bit, or 3‑bit tier based on sensitivity, then uses a Gumbel‑softmax search to find optimal codewords block‑by‑block. After freezing codewords, it recalibrates shared scales via knowledge‑distillation and performs a brief quantization‑aware training, finally selecting the best checkpoint with paired reasoning tests.

By Rhea Sanjay Sukthanker, Pashmina Cameron
llmsefficiency
More like this →