English
Related papers

Related papers: Token-level Accept or Reject: A Micro Alignment Ap…

200 papers

Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high…

Computation and Language · Computer Science 2023-09-21 Yukang Xie , Chengyu Wang , Junbing Yan , Jiyong Zhou , Feiqi Deng , Jun Huang

Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Yuqi Peng , Lingtao Zheng , Yufeng Yang , Yi Huang , Mingfu Yan , Jianzhuang Liu , Shifeng Chen

This paper presents a comprehensive study on the tokenization techniques employed by state-of-the-art large language models (LLMs) and their implications on the cost and availability of services across different languages, especially low…

Computation and Language · Computer Science 2024-10-07 Abrar Rahman , Garry Bowlin , Binit Mohanty , Sean McGunigal

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

Machine Learning · Computer Science 2024-08-02 Gareth Seneque , Lap-Hang Ho , Ariel Kuperman , Nafise Erfanian Saeedi , Jeffrey Molendijk

Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training dynamics across modalities often lead to suboptimal accuracy…

Machine Learning · Computer Science 2026-03-03 Minkyoung Cho , Insu Jang , Shuowei Jin , Zesen Zhao , Adityan Jothi , Ethem F. Can , Min-Hung Chen , Z. Morley Mao

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

Machine Learning · Computer Science 2025-10-22 Jiawei Zhang , Andrew Estornell , David D. Baek , Bo Li , Xiaojun Xu

We present Autoregressive Representation Alignment (ARRA), a new training framework that unlocks global-coherent text-to-image generation in autoregressive LLMs without architectural modifications. Different from prior works that require…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Xing Xie , Jiawei Liu , Ziyue Lin , Huijie Fan , Zhi Han , Yandong Tang , Liangqiong Qu

In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model parameters. However, ICL faces challenges with increasing…

Machine Learning · Computer Science 2024-10-15 Chengsong Huang , Langlin Huang , Jiaxin Huang

In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish…

Computation and Language · Computer Science 2024-06-07 Ziyin Zhang , Yikang Liu , Weifang Huang , Junyu Mao , Rui Wang , Hai Hu

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Desh Raj , Gil Keren , Junteng Jia , Jay Mahadeokar , Ozlem Kalinli

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in…

Information Retrieval · Computer Science 2026-04-21 Hui Wu , Haoquan Zhai , Yuchen Li , Hengyi Cai , Peirong Zhang , Yidan Zhang , Lei Wang , Chunle Wang , Yingyan Hou , Shuaiqiang Wang , Dawei Yin

As large language models (LLMs) are deployed in high-stakes domains like healthcare, understanding how well their decision-making aligns with human preferences and values becomes crucial, especially when we recognize that there is no single…

Computation and Language · Computer Science 2024-10-01 Isaac Kohane

Large language models (LLMs) are increasingly evaluated on single-answer multiple-choice tasks, yet many real-world problems require identifying all correct answers from a set of options. This capability remains underexplored. We introduce…

Computation and Language · Computer Science 2025-10-21 Weijie Xu , Shixian Cui , Xi Fang , Chi Xue , Stephanie Eckman , Chandan K. Reddy

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

Artificial Intelligence · Computer Science 2024-07-08 Jin Peng Zhou , Katie Z Luo , Jingwen Gu , Jason Yuan , Kilian Q. Weinberger , Wen Sun

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the…

Computation and Language · Computer Science 2024-09-02 Yongcheng Zeng , Guoqing Liu , Weiyu Ma , Ning Yang , Haifeng Zhang , Jun Wang

Low-rank adaptation (LoRA) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs). However, fine-tuned LLMs often become overconfident especially when fine-tuned on small datasets. Bayesian methods,…

Machine Learning · Computer Science 2024-02-07 Adam X. Yang , Maxime Robeyns , Xi Wang , Laurence Aitchison

Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models through low-rank matrix approximation, achieving effectiveness in many scenarios. However, its representation capacity is constrained in complex tasks…

As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies,…

Computation and Language · Computer Science 2024-02-20 Junlong Li , Fan Zhou , Shichao Sun , Yikai Zhang , Hai Zhao , Pengfei Liu

Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering. However, most previous PbRL work has not investigated the robustness to…

Machine Learning · Computer Science 2025-06-17 Sara Rajaram , R. James Cotton , Fabian H. Sinz