English
Related papers

Related papers: SeqPO-SiMT: Sequential Policy Optimization for Sim…

200 papers

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

Computation and Language · Computer Science 2025-12-15 Mrinal Rawat , Arkajyoti Chakraborty , Neha Gupta , Roberto Pieraccini

Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for…

Computation and Language · Computer Science 2024-06-04 Zhihao Wen , Jie Zhang , Yuan Fang

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…

Computation and Language · Computer Science 2025-10-28 Lai Wei , Yuting Li , Chen Wang , Yue Wang , Linghe Kong , Weiran Huang , Lichao Sun

Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algorithm for aligning LLMs with human preferences inspired by…

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

Computation and Language · Computer Science 2025-10-16 Hao Wang , Linlong Xu , Heng Liu , Yangyang Liu , Xiaohu Zhao , Bo Zeng , Liangying Shao , Longyue Wang , Weihua Luo , Kaifu Zhang

The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling with a reward model, and learning using feedback on the LLM's own outputs. While performant, this…

Machine Learning · Computer Science 2025-04-29 Michael Noukhovitch , Shengyi Huang , Sophie Xhonneux , Arian Hosseini , Rishabh Agarwal , Aaron Courville

Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our…

Computation and Language · Computer Science 2025-05-21 Zhanglin Wu , Daimeng Wei , Xiaoyu Chen , Hengchao Shang , Jiaxin Guo , Zongyao Li , Yuanchang Luo , Jinlong Yang , Zhiqiang Rao , Hao Yang

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis…

Computation and Language · Computer Science 2025-06-25 Yuqian Fu , Tinghong Chen , Jiajun Chai , Xihuai Wang , Songjun Tu , Guojun Yin , Wei Lin , Qichao Zhang , Yuanheng Zhu , Dongbin Zhao

Recent efforts in fine-tuning language models often rely on automatic data selection, commonly using Nearest Neighbors retrieval from large datasets. However, we theoretically show that this approach tends to select redundant data, limiting…

Machine Learning · Computer Science 2025-02-11 Jonas Hübotter , Sascha Bongni , Ido Hakimi , Andreas Krause

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Computation and Language · Computer Science 2024-12-18 Yuchen Fan , Yuzhong Hong , Qiushi Wang , Junwei Bao , Hongfei Jiang , Yang Song

Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited their adoption. We identify a core latent instability issue…

Computation and Language · Computer Science 2025-09-26 Xilin Wei , Xiaoran Liu , Yuhang Zang , Xiaoyi Dong , Yuhang Cao , Jiaqi Wang , Xipeng Qiu , Dahua Lin

Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on real interpretation data. To illustrate this argument, we…

Computation and Language · Computer Science 2021-10-12 Jinming Zhao , Philip Arthur , Gholamreza Haffari , Trevor Cohn , Ehsan Shareghi

Large Language Models (LLMs) have demonstrated remarkable proficiency in English mathematical reasoning, yet a significant performance disparity persists in multilingual contexts, largely attributed to deficiencies in language…

Computation and Language · Computer Science 2026-03-27 Xu Huang , Zhejian Lai , Zixian Huang , Jiajun Chen , Shujian Huang

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Machine Learning · Computer Science 2026-04-03 Gengsheng Li , Tianyu Yang , Junfeng Fang , Mingyang Song , Mao Zheng , Haiyun Guo , Dan Zhang , Jinqiao Wang , Tat-Seng Chua

Incremental Decoding is an effective framework that enables the use of an offline model in a simultaneous setting without modifying the original model, making it suitable for Low-Latency Simultaneous Speech Translation. However, this…

Computation and Language · Computer Science 2024-01-12 Jiaxin Guo , Zhanglin Wu , Zongyao Li , Hengchao Shang , Daimeng Wei , Xiaoyu Chen , Zhiqiang Rao , Shaojun Li , Hao Yang

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

Gloss-free sign language translation (SLT) is hindered by two key challenges: **inadequate sign representation** that fails to capture nuanced visual cues, and **sentence-level semantic misalignment** in current LLM-based methods, which…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Zhi Rao , Yucheng Zhou , Benjia Zhou , Yiqing Huang , Sergio Escalera , Jun Wan

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

Machine Learning · Computer Science 2025-02-04 Mingze Kong , Zhiyong Wang , Yao Shu , Zhongxiang Dai

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…

Machine Learning · Computer Science 2026-05-01 Jingcheng Deng , Zihao Wei , Liang Pang , Junhong Wu , Shicheng Xu , Zenghao Duan , Huawei Shen

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Machine Learning · Computer Science 2026-05-12 Minmin Zhang , Sina Aghaei , Soroush Saghafian