English
Related papers

Related papers: Restoring Calibration for Aligned Large Language M…

200 papers

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Computation and Language · Computer Science 2025-03-04 Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang

Naive joint training of large language models (LLMs) for multilingual preference alignment can suffer from negative interference. This is a known issue in multilingual training, where conflicting objectives degrade overall performance.…

Computation and Language · Computer Science 2025-11-12 Jiangnan Li , Thuy-Trang Vu , Christian Herold , Amirhossein Tebbifakhr , Shahram Khadivi , Gholamreza Haffari

We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an annotator provides fine-grained feedback by marking ``liked'' and ``disliked''…

Computation and Language · Computer Science 2025-12-30 Sky CH-Wang , Justin Svegliato , Helen Appel , Jason Eisner

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Computation and Language · Computer Science 2024-09-19 Hang Zhou , Chenglong Wang , Yimin Hu , Tong Xiao , Chunliang Zhang , Jingbo Zhu

The rapid advancements in Large Language Models (LLMs) and Large Visual-Language Models (LVLMs) have opened up new opportunities for integrating visual and linguistic modalities. However, effectively aligning these modalities remains…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Sihan Yang , Chenhang Cui , Zihao Zhao , Yiyang Zhou , Weilong Yan , Ying Wei , Huaxiu Yao

Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: \emph{abstention}, where models refrain from generating responses when uncertain; and…

Computation and Language · Computer Science 2025-08-13 Zhengping Jiang , Anqi Liu , Benjamin Van Durme

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Computation and Language · Computer Science 2025-10-28 Amit Agarwal , Hansa Meghwani , Hitesh Laxmichand Patel , Tao Sheng , Sujith Ravi , Dan Roth

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Tao Yu , Yi-Fan Zhang , Chaoyou Fu , Junkang Wu , Jinda Lu , Kun Wang , Xingyu Lu , Yunhang Shen , Guibin Zhang , Dingjie Song , Yibo Yan , Tianlong Xu , Qingsong Wen , Zhang Zhang , Yan Huang , Liang Wang , Tieniu Tan

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless. As an initial foray in…

Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formulating a PLM-based prediction pipeline for NLP tasks, it is…

Computation and Language · Computer Science 2022-10-17 Yuxin Xiao , Paul Pu Liang , Umang Bhatt , Willie Neiswanger , Ruslan Salakhutdinov , Louis-Philippe Morency

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Elmira Amirloo , Jean-Philippe Fauconnier , Christoph Roesmann , Christian Kerl , Rinu Boney , Yusu Qian , Zirui Wang , Afshin Dehghan , Yinfei Yang , Zhe Gan , Peter Grasch

The deployment of machine learning classifiers in high-stakes domains requires well-calibrated confidence scores for model predictions. In this paper we introduce the notion of variable-based calibration to characterize calibration…

Machine Learning · Computer Science 2023-04-07 Markelle Kelly , Padhraic Smyth

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either…

Machine Learning · Computer Science 2026-05-19 Yuhan Huang , Huanran Chen , Yinpeng Dong

While Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, aligning these models with varying human preferences across multiple objectives remains a significant challenge…

Computation and Language · Computer Science 2025-11-17 Biao Liu , Ning Xu , Junming Yang , Xin Geng

Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply…

Machine Learning · Computer Science 2026-04-28 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…

Software Engineering · Computer Science 2026-01-01 David Gros , Prem Devanbu

Large Language Models (LLMs) are increasingly applied in high-stakes domains such as finance, healthcare, and education, where reliable multi-turn interactions with users are essential. However, existing work on confidence estimation and…

Computation and Language · Computer Science 2026-04-08 Zhaohan Zhang , Chengzhengxu Li , Xiaoming Liu , Chao Shen , Ziquan Liu , Ioannis Patras

Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…

Machine Learning · Computer Science 2024-04-15 Lanpei Li , Elia Piccoli , Andrea Cossu , Davide Bacciu , Vincenzo Lomonaco