English
Related papers

Related papers: SFT-GRPO Data Overlap as a Post-Training Hyperpara…

200 papers

Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task success rather than the target semantic predicate. Using agentic compile-fix as the…

Artificial Intelligence · Computer Science 2026-05-11 Jia Li , Yuxin Su , Ting Peng , Hailiang Huang , Yuetang Deng , Michael R. Lyu

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Computation and Language · Computer Science 2026-05-11 Arash Ahmadi , Sarah Sharif , Yaser , Banad

Large language models (LLMs) can now solve complex problems through long chain-of-thought (CoT) reasoning, but the trade-off between performance and token cost remains a central challenge. To address this issue, supervised fine-tuning (SFT)…

Artificial Intelligence · Computer Science 2026-05-28 Kohsei Matsutani , Gouki Minegishi , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo

Task-adaptive pre-training (TAPT) and Self-training (ST) have emerged as the major semi-supervised approaches to improve natural language understanding (NLU) tasks with massive amount of unlabeled data. However, it's unclear whether they…

Computation and Language · Computer Science 2023-02-21 Shiyang Li , Semih Yavuz , Wenhu Chen , Xifeng Yan

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit…

Artificial Intelligence · Computer Science 2026-04-21 Benteng Chen , Weida Wang , Shufei Zhang , Mingbao Lin , Min Zhang

Reinforcement learning (RL) has proven effective in incentivizing the reasoning abilities of large language models (LLMs), but suffers from severe efficiency challenges due to its trial-and-error nature. While the common practice employs…

Computation and Language · Computer Science 2025-10-17 Liang Chen , Xueting Han , Li Shen , Jing Bai , Kam-Fai Wong

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material, in our case explanations of code examples. This research is…

Computers and Society · Computer Science 2025-01-22 Priti Oli , Rabin Banjade , Andrew M. Olney , Vasile Rus

Continual post-training of generative models is widely used, yet a principled understanding of when and why forgetting occurs remains limited. We develop theoretical results under a two-mode mixture abstraction (representing old and new…

Machine Learning · Computer Science 2026-03-13 Krishnakumar Balasubramanian , Shiva Prasad Kasiviswanathan

Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference. However, SFT often performs poorly in real-world settings with label noise,…

Machine Learning · Computer Science 2026-02-04 Punya Syon Pandey , Zhijing Jin

We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcement Learning with…

Machine Learning · Computer Science 2026-05-21 Xingwei Gan , Ying Zhu

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Haoxu Wang , Biao Tian , Yiheng Jiang , Zexu Pan , Shengkui Zhao , Bin Ma , Daren Chen , Xiangang Li

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Robotics · Computer Science 2026-03-09 Liangzhi Shi , Shuaihang Chen , Feng Gao , Yinuo Chen , Kang Chen , Tonghe Zhang , Hongzhi Zang , Weinan Zhang , Chao Yu , Yu Wang

This paper delves into the continuous post-training optimization methods for small language models, and proposes a continuous post-training alignment data construction method for small language models. The core of this method is based on…

Computation and Language · Computer Science 2024-12-24 Keke Zhai

Graph-matching metrics such as Smatch are the de facto standard for evaluating neural semantic parsers, yet they capture surface overlap rather than logical equivalence. We reassess evaluation by pairing graph-matching with automated…

Computation and Language · Computer Science 2025-10-14 Hayate Funakura , Hyunsoo Kim , Koji Mineshima

Modern large language models (LLMs) are increasingly fine-tuned via reinforcement learning from human feedback (RLHF) or related reward optimisation schemes. While such procedures improve perceived helpfulness, we investigate whether…

Machine Learning · Computer Science 2026-04-14 Subramanyam Sahoo

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL…

Machine Learning · Computer Science 2026-03-18 Wenhao Zhang , Yuexiang Xie , Yuchang Sun , Yanxi Chen , Guoyin Wang , Yaliang Li , Bolin Ding , Jingren Zhou

Recent mixed-policy optimization methods for LLM reasoning that interleave or blend supervised and reinforcement learning signals report improvements over the standard SFT-then-RL pipeline. We show that numerous recently published research…

Machine Learning · Computer Science 2026-04-28 Alexis Limozin , Eduard Durech , Torsten Hoefler , Imanol Schlag , Valentina Pyatkin

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Machine Learning · Computer Science 2025-01-15 Yaowen Ye , Cassidy Laidlaw , Jacob Steinhardt

We present a two-stage fine-tuning approach to make the large language model Qwen3 14B "think" natively in Korean. In the first stage, supervised fine-tuning (SFT) on a high-quality Korean reasoning dataset establishes a strong foundation…

Computation and Language · Computer Science 2025-08-15 Jungyup Lee , Jemin Kim , Sang Park , SeungJae Lee