English
Related papers

Related papers: ECLIPTICA -- A Framework for Switchable LLM Alignm…

200 papers

Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to update at inference time without labeled data, typically via…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Marc Lafon , Gustavo Adolfo Vargas Hakim , Clément Rambour , Christian Desrosier , Nicolas Thome

Alignment serves as an important step to steer large language models (LLMs) towards human preferences. In this paper, we propose an automatic way to construct contrastive data for LLM, using preference pairs from multiple models of varying…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Machine Learning · Computer Science 2025-12-15 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Shouhong Ding , Yuan Xie

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu

Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates the critical role of data engineering in instruction tuning…

Computation and Language · Computer Science 2024-04-17 Wei Liu , Weihao Zeng , Keqing He , Yong Jiang , Junxian He

Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user…

Computation and Language · Computer Science 2023-05-22 Chunting Zhou , Pengfei Liu , Puxin Xu , Srini Iyer , Jiao Sun , Yuning Mao , Xuezhe Ma , Avia Efrat , Ping Yu , Lili Yu , Susan Zhang , Gargi Ghosh , Mike Lewis , Luke Zettlemoyer , Omer Levy

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…

Computation and Language · Computer Science 2023-10-24 Zihan Zhang , Meng Fang , Ling Chen , Mohammad-Reza Namazi-Rad

Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve this by using small guidance models to modify token…

Artificial Intelligence · Computer Science 2025-11-14 Sarat Chandra Bobbili , Ujwal Dinesha , Dheeraj Narasimha , Srinivas Shakkottai

We propose Frictive Policy Optimization (FPO), a framework for learning language model policies that regulate not only what to say, but when and how to intervene in order to manage epistemic and normative risk. Unlike standard alignment…

Computation and Language · Computer Science 2026-04-29 James Pustejovsky , Nikhil Krishnaswamy

Despite their strong ability to retrieve knowledge in English, current large language models show imbalance abilities in different languages. Two approaches are proposed to address this, i.e., multilingual pretraining and multilingual…

Computation and Language · Computer Science 2024-04-09 Changjiang Gao , Hongda Hu , Peng Hu , Jiajun Chen , Jixing Li , Shujian Huang

In the pursuit of advancing natural language processing for the Italian language, we introduce a state-of-the-art Large Language Model (LLM) based on the novel Meta LLaMA-3 model: LLaMAntino-3-ANITA-8B-Inst-DPO-ITA. We fine-tuned the…

Computation and Language · Computer Science 2024-05-14 Marco Polignano , Pierpaolo Basile , Giovanni Semeraro

High-quality instruction data is critical for LLM alignment, yet existing open-source datasets often lack efficiency, requiring hundreds of thousands of examples to approach proprietary performance. In this work, we find that beyond the…

Computation and Language · Computer Science 2026-04-10 Shangjian Yin , Shining Liang , Wenbiao Ding , Yuli Qian , Zhouxing Shi , Hongzhi Li , Yutao Xie

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

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Machine Learning · Computer Science 2024-02-27 Tianchi Cai , Xierui Song , Jiyan Jiang , Fei Teng , Jinjie Gu , Guannan Zhang

Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing…

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate…

Computation and Language · Computer Science 2024-04-16 Geyang Guo , Ranchi Zhao , Tianyi Tang , Wayne Xin Zhao , Ji-Rong Wen

We present \llinstruct: An 8B instruction-tuned model that is designed to generate content for English Language Proficiency Assessments (ELPA) and related applications. Our work involves creating a new dataset of 70K instructions and…

Computation and Language · Computer Science 2024-10-15 Debanjan Ghosh , Sophia Chan

Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these…

Computation and Language · Computer Science 2026-02-13 Xin Xu , Yan Xu , Tianhao Chen , Yuchen Yan , Chengwu Liu , Zaoyu Chen , Yufei Wang , Yichun Yin , Yasheng Wang , Lifeng Shang , Qun Liu , Lu Yin
‹ Prev 1 2 3 10 Next ›