English
Related papers

Related papers: KARMA: Karma-Aligned Reward Model Adaptation

200 papers

Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting,…

Large Language Models (LLMs) are increasingly deployed in human-centric applications, yet they often fail to provide substantive emotional support. While Reinforcement Learning (RL) has been utilized to enhance empathy of LLMs, existing…

Computation and Language · Computer Science 2026-01-19 Chengbing Wang , Wuqiang Zheng , Yang Zhang , Fengbin Zhu , Junyi Cheng , Yi Xie , Wenjie Wang , Fuli Feng

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Integrating robotics into everyday scenarios like tutoring or physical training requires robots capable of adaptive, socially engaging, and goal-oriented interactions. While Large Language Models show promise in human-like communication,…

Robotics · Computer Science 2025-04-03 Luca Garello , Giulia Belgiovine , Gabriele Russo , Francesco Rea , Alessandra Sciutti

Instruction tuning of open-source large language models (LLMs) like LLaMA, using direct outputs from more powerful LLMs such as Instruct-GPT and GPT-4, has proven to be a cost-effective way to align model behaviors with human preferences.…

Computation and Language · Computer Science 2023-10-23 Haoran Li , Yiran Liu , Xingxing Zhang , Wei Lu , Furu Wei

To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue…

Computation and Language · Computer Science 2025-01-28 Kai Yoshida , Masahiro Mizukami , Seiya Kawano , Canasai Kruengkrai , Hiroaki Sugiyama , Koichiro Yoshino

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human…

Machine Learning · Computer Science 2024-05-24 Andi Peng , Yuying Sun , Tianmin Shu , David Abel

Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike more structured texts like news, chat conversations are…

Computation and Language · Computer Science 2024-03-14 Sweta Agrawal , Amin Farajian , Patrick Fernandes , Ricardo Rei , André F. T. Martins

Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face…

Machine Learning · Computer Science 2025-01-10 Yun Qu , Yuhang Jiang , Boyuan Wang , Yixiu Mao , Cheems Wang , Chang Liu , Xiangyang Ji

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences…

Computation and Language · Computer Science 2026-04-21 Hongru Cai , Yongqi Li , Tiezheng Yu , Fengbin Zhu , Wenjie Wang , Fuli Feng , Wenjie Li

Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared goals. A common approach for learning this cooperative…

Multiagent Systems · Computer Science 2025-02-25 Kartik Nagpal , Dayi Dong , Jean-Baptiste Bouvier , Negar Mehr

Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…

Artificial Intelligence · Computer Science 2025-02-11 Bidipta Sarkar , Warren Xia , C. Karen Liu , Dorsa Sadigh

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

Computation and Language · Computer Science 2026-04-10 Panatchakorn Anantaprayoon , Nataliia Babina , Nima Asgharbeygi , Jad Tarifi

Conversational recommendation systems (CRS) leverage contextual information from conversations to generate recommendations but often struggle due to a lack of collaborative filtering (CF) signals, which capture user-item interaction…

Information Retrieval · Computer Science 2025-02-12 Ahmad Bin Rabiah , Nafis Sadeq , Julian McAuley

Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavior can emerge requires expert knowledge, especially for…

Machine Learning · Computer Science 2024-06-25 Timo Kaufmann , Jannis Blüml , Antonia Wüst , Quentin Delfosse , Kristian Kersting , Eyke Hüllermeier

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

Navigating robots through unstructured terrains is challenging, primarily due to the dynamic environmental changes. While humans adeptly navigate such terrains by using context from their observations, creating a similar context-aware…

Recent developments in Large Language Models (LLMs) have shifted from pre-training scaling to post-training and test-time scaling. Across these developments, a key unified paradigm has arisen: Learning from Rewards, where reward signals act…

Computation and Language · Computer Science 2025-06-13 Xiaobao Wu

Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, the speaker's sarcastic intent is not always apparent without additional context. Focusing on social media discussions, we…

Computation and Language · Computer Science 2018-08-29 Debanjan Ghosh , Alexander R. Fabbri , Smaranda Muresan

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Computation and Language · Computer Science 2025-01-09 Shujun Liu , Xiaoyu Shen , Yuhang Lai , Siyuan Wang , Shengbin Yue , Zengfeng Huang , Xuanjing Huang , Zhongyu Wei