English
Related papers

Related papers: Self-Improving Tabular Language Models via Iterati…

200 papers

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

Computation and Language · Computer Science 2024-10-28 Alizée Pace , Jonathan Mallinson , Eric Malmi , Sebastian Krause , Aliaksei Severyn

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Computation and Language · Computer Science 2025-07-01 Yi-Chen Li , Tian Xu , Yang Yu , Xuqin Zhang , Xiong-Hui Chen , Zhongxiang Ling , Ningjing Chao , Lei Yuan , Zhi-Hua Zhou

Large language models (LLMs) have shown promise in simulating human-like social behaviors. Social graphs provide high-quality supervision signals that encode both local interactions and global network structure, yet they remain…

Social and Information Networks · Computer Science 2026-04-14 Jiarui Ji , Zehua Zhang , Zhewei Wei , Bin Tong , Guan Wang , Bo Zheng

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

Artificial Intelligence · Computer Science 2026-04-15 Haozhe Wang , Cong Wei , Weiming Ren , Jiaming Liu , Fangzhen Lin , Wenhu Chen

Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent work augments RL with textual critiques through prompting or…

Computation and Language · Computer Science 2026-01-28 Hanyang Wang , Lu Wang , Chaoyun Zhang , Tianjun Mao , Si Qin , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang

Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages…

Computation and Language · Computer Science 2025-02-27 Wen Yang , Junhong Wu , Chen Wang , Chengqing Zong , Jiajun Zhang

In the realm of natural language processing, the understanding of tabular data has perpetually stood as a focal point of scholarly inquiry. The emergence of expansive language models, exemplified by the likes of ChatGPT, has ushered in a…

Computation and Language · Computer Science 2023-08-29 Hengyuan Zhang , Peng Chang , Zongcheng Ji

Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like…

Machine Learning · Computer Science 2026-01-21 Xingtai Lv , Yuxin Zuo , Youbang Sun , Hongyi Liu , Yuntian Wei , Zhekai Chen , Xuekai Zhu , Kaiyan Zhang , Bingning Wang , Ning Ding , Bowen Zhou

Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive process. To reduce labor costs, we propose a self-supervised…

Computation and Language · Computer Science 2024-03-05 Shuo Yang , Gjergji Kasneci

Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text accuracy can reduce aesthetic quality and instruction-following capability. Although…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Yaohou Fan , Qingzhong Wang , Yongsong Huang , Junyi Liu , Tomo Miyazaki , Shinichiro Omachi

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…

Computation and Language · Computer Science 2025-07-08 Zhuohao Yu , Jiali Zeng , Weizheng Gu , Yidong Wang , Jindong Wang , Fandong Meng , Jie Zhou , Yue Zhang , Shikun Zhang , Wei Ye

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…

Computation and Language · Computer Science 2025-01-15 Zhongxiang Sun , Qipeng Wang , Weijie Yu , Xiaoxue Zang , Kai Zheng , Jun Xu , Xiao Zhang , Song Yang , Han Li

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…

Machine Learning · Computer Science 2023-07-17 Hui Yuan , Kaixuan Huang , Chengzhuo Ni , Minshuo Chen , Mengdi Wang

Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while…

Machine Learning · Computer Science 2025-09-25 Emmanouil Panagiotou , Benoît Ronval , Arjun Roy , Ludwig Bothmann , Bernd Bischl , Siegfried Nijssen , Eirini Ntoutsi

By compressing diverse narratives, LLMs go beyond memorization, achieving intelligence by capturing generalizable causal relationships. However, they suffer from local 'representation gaps' due to insufficient training data diversity,…

Machine Learning · Computer Science 2024-08-30 Fangyuan Yu , Hardeep Singh Arora , Matt Johnson

Evaluating AI tutor responses requires more than factual correctness: tutors must identify mistakes, locate errors, provide guidance, and offer actionable next steps. We present GRADE, a systematic study of open-source models for…

Computation and Language · Computer Science 2026-05-28 Parth Bhalerao , Jeromy Chang , David Chou , Oana Ignat

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language…

Machine Learning · Computer Science 2025-06-18 Mingkang Zhu , Xi Chen , Zhongdao Wang , Bei Yu , Hengshuang Zhao , Jiaya Jia

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by…

Machine Learning · Computer Science 2025-01-22 Zhepeng Cen , Yao Liu , Siliang Zeng , Pratik Chaudhari , Huzefa Rangwala , George Karypis , Rasool Fakoor

The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context alone, agents have access to hierarchical schemas containing…

Computation and Language · Computer Science 2023-03-20 A. Coca , B. H. Tseng , W. Lin , B. Byrne

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…

Computation and Language · Computer Science 2023-12-18 Jie Ren , Yao Zhao , Tu Vu , Peter J. Liu , Balaji Lakshminarayanan