English
Related papers

Related papers: Rethinking Supervised Fine-Tuning: Emphasizing Key…

200 papers

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive…

Computation and Language · Computer Science 2024-06-18 Che Zhang , Zhenyang Xiao , Chengcheng Han , Yixin Lian , Yuejian Fang

Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted…

Computation and Language · Computer Science 2023-10-20 Eric Mitchell , Rafael Rafailov , Archit Sharma , Chelsea Finn , Christopher D. Manning

Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation,…

Computation and Language · Computer Science 2026-04-21 Shaojie Wang , Liang Zhang

Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the…

Computation and Language · Computer Science 2024-04-30 Tingfeng Hui , Zhenyu Zhang , Shuohuan Wang , Weiran Xu , Yu Sun , Hua Wu

The post-training of LLMs, which typically consists of the supervised fine-tuning (SFT) stage and the preference learning stage (RLHF or DPO), is crucial to effective and safe LLM applications. The widely adopted approach in post-training…

Machine Learning · Computer Science 2025-11-11 Heshan Fernando , Han Shen , Parikshit Ram , Yi Zhou , Horst Samulowitz , Nathalie Baracaldo , Tianyi Chen

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Computation and Language · Computer Science 2023-09-06 Peiyi Wang , Lei Li , Liang Chen , Feifan Song , Binghuai Lin , Yunbo Cao , Tianyu Liu , Zhifang Sui

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its nature. At the same time, recent works indicate the…

Computation and Language · Computer Science 2024-02-12 Ming Shen

Large Language Models (LLMs) are gaining significant popularity in recent years for specialized tasks using prompts due to their low computational cost. Standard methods like prefix tuning utilize special, modifiable tokens that lack…

Computation and Language · Computer Science 2024-10-14 Nusrat Jahan Prottasha , Asif Mahmud , Md. Shohanur Islam Sobuj , Prakash Bhat , Md Kowsher , Niloofar Yousefi , Ozlem Ozmen Garibay

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

Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific…

Computation and Language · Computer Science 2024-12-31 Jia Liu , Yue Wang , Zhiqi Lin , Min Chen , Yixue Hao , Long Hu

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remains unclear. We revisit the common claim that ``SFT memorizes,…

Machine Learning · Computer Science 2026-05-12 Hangzhan Jin , Sitao Luan , Tianwei Ni , Sicheng Lyu , Guillaume Rabusseau , Reihaneh Rabbany , Doina Precup , Mohammad Hamdaqa

Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…

Software Engineering · Computer Science 2026-01-14 Lishui Fan , Zhongxin Liu , Haoye Wang , Lingfeng Bao , Xin Xia , Shanping Li

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by…

Supervised fine-tuning (SFT) is a standard approach for adapting large language models to specialized domains, yet its application to protein sequence modeling and protein language models (PLMs) remains ad hoc. This is in part because…

Machine Learning · Computer Science 2025-12-11 Amin Tavakoli , Raswanth Murugan , Ozan Gokdemir , Arvind Ramanathan , Frances Arnold , Anima Anandkumar

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all…

Computation and Language · Computer Science 2024-10-14 Changhun Lee , Jun-gyu Jin , Younghyun Cho , Eunhyeok Park

Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning…

Artificial Intelligence · Computer Science 2026-03-20 Shaked Perek , Ben Wiesel , Avihu Dekel , Nimrod Shabtay , Eli Schwartz

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…

Computation and Language · Computer Science 2025-02-06 Wei Chen , Zhen Huang , Liang Xie , Binbin Lin , Houqiang Li , Le Lu , Xinmei Tian , Deng Cai , Yonggang Zhang , Wenxiao Wang , Xu Shen , Jieping Ye

Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user…

Computation and Language · Computer Science 2025-02-10 Yifan Peng , Krishna C. Puvvada , Zhehuai Chen , Piotr Zelasko , He Huang , Kunal Dhawan , Ke Hu , Shinji Watanabe , Jagadeesh Balam , Boris Ginsburg