English
Related papers

Related papers: Implicit Turn-Wise Policy Optimization for Proacti…

200 papers

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans…

Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforcement learning (RL). This separation creates a complex, resource-intensive pipeline and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Songshuo Lu , Hua Wang , Zhi Chen , Yaohua Tang

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…

Computation and Language · Computer Science 2026-03-26 Rahul Singhal , Pradyumna Tambwekar , Karime Maamari

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…

Computation and Language · Computer Science 2026-01-27 Wengao Ye , Yan Liang , Lianlei Shan

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

Computation and Language · Computer Science 2025-08-26 Chenxu Yang , Ruipeng Jia , Mingyu Zheng , Naibin Gu , Zheng Lin , Siyuan Chen , Weichong Yin , Hua Wu , Weiping Wang

Preference Optimization (PO), is gaining popularity as an alternative choice of Proximal Policy Optimization (PPO) for aligning Large Language Models (LLMs). Recent research on aligning LLMs iteratively with synthetic or partially synthetic…

Computation and Language · Computer Science 2024-09-16 Yaojie Shen , Xinyao Wang , Yulei Niu , Ying Zhou , Lexin Tang , Libo Zhang , Fan Chen , Longyin Wen

We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The agent must follow a multi-stage Standard Operating Procedure (SOP) and strict guardrails (no…

Computation and Language · Computer Science 2026-04-30 Xia Zeng , Yihan Chen , Luhui Liu , Chao Luo , Ye Chen , Zhuoran Zhuang

Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opinion words. Existing models typically learn from the final polarity label, which provides…

Computation and Language · Computer Science 2026-05-21 Yaping Chai , Haoran Xie , Joe S. Qin

Recent work reports gains in neural text-to-speech (TTS) with Group Relative Policy Optimization (GRPO). However, in the absence of a verifiable reward for \textit{prosody}, GRPO trained on transcription-oriented signals (CER/NLL) lowers…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Seungyoun Shin , Dongha Ahn , Jiwoo Kim , Sungwook Jeon

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

Computation and Language · Computer Science 2024-06-18 Jie Liu , Zhanhui Zhou , Jiaheng Liu , Xingyuan Bu , Chao Yang , Han-Sen Zhong , Wanli Ouyang

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Machine Learning · Computer Science 2026-05-18 Xiaoqiang Lin , Arun Verma , Zhongxiang Dai , Daniela Rus , See-Kiong Ng , Bryan Kian Hsiang Low

Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…

Computation and Language · Computer Science 2025-01-23 Qi Gou , Cam-Tu Nguyen

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2023-01-05 Daniel Shin , Anca D. Dragan , Daniel S. Brown

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Computation and Language · Computer Science 2025-11-03 Fenia Christopoulou , Ronald Cardenas , Gerasimos Lampouras , Haitham Bou-Ammar , Jun Wang

Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping…

Computation and Language · Computer Science 2026-02-24 Yinhan He , Yaochen Zhu , Mingjia Shi , Wendy Zheng , Lin Su , Xiaoqing Wang , Qi Guo , Jundong Li

In social impact optimization, AI decision systems often rely on solvers that optimize well-calibrated mathematical objectives. However, these solvers cannot directly accommodate evolving human preferences, typically expressed in natural…

Artificial Intelligence · Computer Science 2025-09-23 Guojun Xiong , Milind Tambe

Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimized with trajectory-level RL algorithms such as GRPO. However,…

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei