English
Related papers

Related papers: How Does Prefix Matter in Reasoning Model Tuning?

200 papers

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…

Human-Computer Interaction · Computer Science 2026-03-10 Xin Sun , Shu Wei , Jos A Bosch , Isao Echizen , Saku Sugawara , Abdallah El Ali

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.…

Computation and Language · Computer Science 2021-09-08 Kaixin Ma , Filip Ilievski , Jonathan Francis , Satoru Ozaki , Eric Nyberg , Alessandro Oltramari

Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual…

Computation and Language · Computer Science 2025-09-30 Shulin Huang , Yiran Ding , Junshu Pan , Yue Zhang

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts…

Computation and Language · Computer Science 2021-09-03 Brian Lester , Rami Al-Rfou , Noah Constant

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…

Machine Learning · Computer Science 2026-02-11 Shijie Zhang , Xiang Guo , Rujun Guo , Shaoyu Liu , Xiaozhao Wang , Guanjun Jiang , Kevin Zhang

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Computation and Language · Computer Science 2025-06-05 Chaeyun Jang , Moonseok Choi , Yegon Kim , Hyungi Lee , Juho Lee

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Computation and Language · Computer Science 2025-06-05 Mohammadamin Shafiei , Hamidreza Saffari , Nafise Sadat Moosavi

As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly…

A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models are susceptible to spurious features that are not causally…

Machine Learning · Computer Science 2026-05-19 Yupei Yang , Lin Yang , Wanxi Deng , Lin Qu , Fan Feng , Biwei Huang , Shikui Tu , Lei Xu

Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls. To bootstrap more efficient RL, we consider reusing old…

Machine Learning · Computer Science 2026-02-04 Amrith Setlur , Zijian Wang , Andrew Cohen , Paria Rashidinejad , Sang Michael Xie

In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain…

The limited reasoning capabilities of small language models (SLMs) cast doubt on their suitability for tasks demanding deep, multi-step logical deduction. This paper introduces a framework called Small Reasons, Large Hints (SMART), which…

Computation and Language · Computer Science 2025-06-03 Yujin Kim , Euiin Yi , Minu Kim , Se-Young Yun , Taehyeon Kim

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the…

Cryptography and Security · Computer Science 2026-03-04 Jingyuan Xie , Wenjie Wang , Ji Wu , Jiandong Gao

The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also arise from time to time, making the progress illusive.…

Machine Learning · Computer Science 2026-02-02 Hong Xie , Xiao Hu , Tao Tan , Haoran Gu , Xin Li , Jianyu Han , Defu Lian , Enhong Chen

Recently, prefix-tuning was proposed to efficiently adapt pre-trained language models to a broad spectrum of natural language classification tasks. It leverages soft prefix as task-specific indicators and language verbalizers as…

Computation and Language · Computer Science 2024-02-14 Yang Li , Canran Xu , Guodong Long , Tao Shen , Chongyang Tao , Jing Jiang

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Machine Learning · Computer Science 2026-02-17 Jing-Cheng Pang , Liang Lu , Xian Tang , Kun Jiang , Sijie Wu , Kai Zhang , Xubin Li

Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We introduce…

Computation and Language · Computer Science 2026-05-28 Shengmin Piao , Sanghyun Park

Answer set programming is one of the most praised frameworks for declarative programming in general and non-monotonic reasoning in particular. There has been many efforts to extend stable model semantics so that answer set programs can use…

Logic in Computer Science · Computer Science 2012-12-04 Shahab Tasharrofi