English
Related papers

Related papers: Mind the Gap: Conformative Decoding to Improve Out…

200 papers

Large Language Models (LLMs) have shown significant capability across various tasks, with their real-world effectiveness often driven by prompt design. While recent research has focused on optimizing prompt content, the role of prompt…

Computation and Language · Computer Science 2025-05-22 Yuanye Liu , Jiahang Xu , Li Lyna Zhang , Qi Chen , Xuan Feng , Yang Chen , Zhongxin Guo , Yuqing Yang , Peng Cheng

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…

Computation and Language · Computer Science 2025-02-11 Amir Saeidi , Shivanshu Verma , Md Nayem Uddin , Chitta Baral

Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into…

Computation and Language · Computer Science 2024-01-30 Minghao Wu , Abdul Waheed , Chiyu Zhang , Muhammad Abdul-Mageed , Alham Fikri Aji

This study investigates semantic uncertainty in large language model (LLM) outputs across different decoding methods, focusing on emerging techniques like speculative sampling and chain-of-thought (CoT) decoding. Through experiments on…

Computation and Language · Computer Science 2025-06-24 Darius Foodeei , Simin Fan , Martin Jaggi

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

Computation and Language · Computer Science 2025-10-31 Zhenqing Ling , Daoyuan Chen , Liuyi Yao , Qianli Shen , Yaliang Li , Ying Shen

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

Computation and Language · Computer Science 2024-07-08 Yuyan Chen , Zhihao Wen , Ge Fan , Zhengyu Chen , Wei Wu , Dayiheng Liu , Zhixu Li , Bang Liu , Yanghua Xiao

Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity of the generated outputs. To benchmark the approach, we…

Computation and Language · Computer Science 2026-01-27 Pulin Agrawal , Prasoon Goyal

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Computation and Language · Computer Science 2025-05-27 Xiaochen Zhu , Caiqi Zhang , Tom Stafford , Nigel Collier , Andreas Vlachos

Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding…

Computation and Language · Computer Science 2026-01-15 Qian Cao , Yahui Liu , Wei Bi , Yi Zhao , Ruihua Song , Xiting Wang , Ruiming Tang , Guorui Zhou , Han Li

LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We…

Computation and Language · Computer Science 2025-02-27 Diana Marie Schenke , Timo Baumann

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel and structural source…

Computation and Language · Computer Science 2026-04-17 Shaoyang Xu , Wenxuan Zhang

Diverse language model responses are crucial for creative generation, open-ended tasks, and self-improvement training. We show that common diversity metrics, and even reward models used for preference optimization, systematically bias…

Computation and Language · Computer Science 2026-02-02 Vijeta Deshpande , Debasmita Ghose , John D. Patterson , Roger Beaty , Anna Rumshisky

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer…

Computation and Language · Computer Science 2024-11-06 Shengzhi Li , Rongyu Lin , Shichao Pei

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms.…

Machine Learning · Computer Science 2025-11-04 Jian Yao , Ran Cheng , Xingyu Wu , Jibin Wu , Kay Chen Tan

Large language models often suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. This critically degrades the user experience, especially in low-resource settings. We…

Computation and Language · Computer Science 2025-07-22 Nahyun Lee , Yeongseo Woo , Hyunwoo Ko , Guijin Son

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

Computation and Language · Computer Science 2023-11-29 Utsav Garg , Erhan Bas

Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks. However, the procedure to optimizing the mixing of instruction datasets for LLM fine-tuning is still poorly understood. This…

Computation and Language · Computer Science 2024-02-20 Renxi Wang , Haonan Li , Minghao Wu , Yuxia Wang , Xudong Han , Chiyu Zhang , Timothy Baldwin

Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code generation performance of pre-trained Code LLMs. In this…

Computation and Language · Computer Science 2024-02-15 Yejie Wang , Keqing He , Guanting Dong , Pei Wang , Weihao Zeng , Muxi Diao , Yutao Mou , Mengdi Zhang , Jingang Wang , Xunliang Cai , Weiran Xu

Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs, filters or reweights data based on this verification, and…

Computation and Language · Computer Science 2025-02-26 Yuda Song , Hanlin Zhang , Carson Eisenach , Sham Kakade , Dean Foster , Udaya Ghai

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei