English
Related papers

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

200 papers

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…

Computation and Language · Computer Science 2025-03-05 Ke Ji , Jiahao Xu , Tian Liang , Qiuzhi Liu , Zhiwei He , Xingyu Chen , Xiaoyuan Liu , Zhijie Wang , Junying Chen , Benyou Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In this work, we study the test-time scaling of language models…

Machine Learning · Computer Science 2025-07-25 Matthias Otth , Jonas Hübotter , Ido Hakimi , Andreas Krause

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix token parameters for…

Computation and Language · Computer Science 2022-03-22 Zonghan Yang , Yang Liu

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…

Machine Learning · Computer Science 2024-04-10 Aleksandar Petrov , Philip H. S. Torr , Adel Bibi

As Reinforcement Learning with Verifiable Rewards (RLVR) substantially improves the reasoning abilities of large language models (LLMs), a new bottleneck emerges: more training problems become saturated, that is, the LLM answers the…

Machine Learning · Computer Science 2026-05-12 Minwu Kim , Safal Shrestha , Anubhav Shrestha , Keith Ross

Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically…

The invention of transformer-based models such as BERT, GPT, and RoBERTa has enabled researchers and financial companies to finetune these powerful models and use them in different downstream tasks to achieve state-of-the-art performance.…

Computation and Language · Computer Science 2022-11-11 Sudhandar Balakrishnan , Yihao Fang , Xioadan Zhu

Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many nature of language by forcing alignment with a single…

Computation and Language · Computer Science 2026-05-07 Tao Liu , Taiqiang Wu , Runming Yang , Shaoning Sun , Junjie Wang , Yujiu Yang

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Machine Learning · Computer Science 2026-03-03 Vivswan Shah , Randy Cogill , Hanwei Yue , Gopinath Chennupati , Rinat Khaziev

Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, $P(y=1 \mid o_{1:t})$, using prefix-safe observations. Sequential Bayesian Belief Tracking (SBBT)…

Artificial Intelligence · Computer Science 2026-05-28 Zhenghan Song , Yunyi Li , Yulong Liu

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing…

Machine Learning · Computer Science 2025-11-17 Sirui Liang , Pengfei Cao , Jian Zhao , Cong Huang , Jun Zhao , Kang Liu

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate…

Computation and Language · Computer Science 2025-06-09 Sanchit Kabra , Akshita Jha , Chandan K. Reddy

Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we…

Computation and Language · Computer Science 2021-01-05 Xiang Lisa Li , Percy Liang

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

Computation and Language · Computer Science 2022-05-24 Marjan Ghazvininejad , Vladimir Karpukhin , Vera Gor , Asli Celikyilmaz

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…

Artificial Intelligence · Computer Science 2025-05-26 Wang Yang , Zirui Liu , Hongye Jin , Qingyu Yin , Vipin Chaudhary , Xiaotian Han

Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content…

Artificial Intelligence · Computer Science 2025-12-19 Jirui Yang , Hengqi Guo , Zhihui Lu , Yi Zhao , Yuansen Zhang , Shijing Hu , Qiang Duan , Yinggui Wang , Tao Wei

Parameter-Efficient Fine-Tuning (PEFT) methods have become crucial for rapidly adapting large language models (LLMs) to downstream tasks. Prefix-Tuning, an early and effective PEFT technique, demonstrated the ability to achieve performance…

Computation and Language · Computer Science 2026-04-21 Haonan Wang , Brian Chen , Siquan Li , Xinhe Liang , Hwee Kuan Lee , Kenji Kawaguchi , Tianyang Hu

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

Computation and Language · Computer Science 2024-07-01 Shouchang Guo , Sonam Damani , Keng-hao Chang

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Computation and Language · Computer Science 2025-12-22 Kangwei Liu , Mengru Wang , Yujie Luo , Lin Yuan , Mengshu Sun , Lei Liang , Zhiqiang Zhang , Jun Zhou , Bryan Hooi , Shumin Deng
‹ Prev 1 2 3 10 Next ›