English
Related papers

Related papers: Subspace Control: Turning Constrained Model Steeri…

200 papers

Supervised fine-tuning (SFT) is widely used to align large language models (LLMs) with information extraction (IE) tasks, such as named entity recognition (NER). However, annotating such fine-grained labels and training domain-specific…

Computation and Language · Computer Science 2025-07-01 Zhuojun Ding , Wei Wei , Chenghao Fan

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

Computation and Language · Computer Science 2025-01-28 Leonardo Ranaldi , Andrè Freitas

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2025-02-21 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Dinesh Khandelwal , Dinesh Raghu , Sachindra Joshi

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Artificial Intelligence · Computer Science 2025-03-28 Jiaqi Han , Jingwen Ye , Shunyu Liu , Haofei Zhang , Jie Song , Zunlei Feng , Mingli Song

Set constraints provide a highly general way to formulate program analyses. However, solving arbitrary boolean combinations of set constraints is NEXPTIME-hard. Moreover, while theoretical algorithms to solve arbitrary set constraints…

Programming Languages · Computer Science 2020-03-03 Joseph Eremondi

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety alignment (uncensored) compare with more heavily aligned (censored) counterparts in a…

Computation and Language · Computer Science 2026-05-05 Sanjeeevan Selvaganapathy , Mehwish Nasim

While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation between these stages remain largely underexplored. Current…

Artificial Intelligence · Computer Science 2026-04-14 Yang Zhao , Yangou Ouyang , Xiao Ding , Hepeng Wang , Bibo Cai , Kai Xiong , Jinglong Gao , Zhouhao Sun , Li Du , Bing Qin , Ting Liu

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely…

Computation and Language · Computer Science 2022-10-12 Yuanxin Liu , Fandong Meng , Zheng Lin , Jiangnan Li , Peng Fu , Yanan Cao , Weiping Wang , Jie Zhou

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Computation and Language · Computer Science 2023-02-10 Joel Jang , Seungone Kim , Seonghyeon Ye , Doyoung Kim , Lajanugen Logeswaran , Moontae Lee , Kyungjae Lee , Minjoon Seo

Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies for safety intervention across diverse tasks. To better…

Cryptography and Security · Computer Science 2026-04-10 Weiwei Qi , Zefeng Wu , Tianhang Zheng , Zikang Zhang , Xiaojun Jia , Zhan Qin , Kui Ren

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Computation and Language · Computer Science 2024-10-10 Tao Meng , Ninareh Mehrabi , Palash Goyal , Anil Ramakrishna , Aram Galstyan , Richard Zemel , Kai-Wei Chang , Rahul Gupta , Charith Peris

Large pre-trained language models have been used to generate code,providing a flexible interface for synthesizing programs from natural language specifications. However, they often violate syntactic and semantic rules of their output…

Machine Learning · Computer Science 2022-01-28 Gabriel Poesia , Oleksandr Polozov , Vu Le , Ashish Tiwari , Gustavo Soares , Christopher Meek , Sumit Gulwani

The large language model (LLM) is typically integrated into the mainstream optimization protocol. No work has questioned whether maintaining the model integrity is \textit{indispensable} for promising performance. In this work, we introduce…

Computation and Language · Computer Science 2026-03-17 Mingyuan Zhang , Yue Bai , Huan Wang , Yizhou Wang , Qihua Dong , Yitian Zhang , Yun Fu

Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal…

Machine Learning · Computer Science 2025-05-20 Ali Gholamzadeh , Noor Sajid

By the recent advances in computer technology leading to the invention of more powerful processors, the importance of creating models using data training is even greater than ever. Given the significance of this issue, this work tries to…

Optimization and Control · Mathematics 2023-12-27 Saman Khoramian

Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form…

Artificial Intelligence · Computer Science 2026-03-12 Lu Ma , Hao Liang , Meiyi Qiang , Lexiang Tang , Xiaochen Ma , Zhen Hao Wong , Junbo Niu , Chengyu Shen , Runming He , Yanhao Li , Bin Cui , Wentao Zhang

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Junghwan Park , Woojin Cho , Junhyuk Heo , Darongsae Kwon , Kookjin Lee

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…

Computation and Language · Computer Science 2026-01-13 Zijing Wang , Yongkang Liu , Mingyang Wang , Ercong Nie , Deyuan Chen , Zhengjie Zhao , Shi Feng , Daling Wang , Xiaocui Yang , Yifei Zhang , Hinrich Schütze

Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify diverse objectives…

Software Engineering · Computer Science 2026-03-12 Amal Akli , Maxime Cordy , Mike Papadakis , Yves Le Traon