English
Related papers

Related papers: Weak Reward Model Transforms Generative Models int…

200 papers

Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, these agents often exploit spurious correlations in the…

Artificial Intelligence · Computer Science 2025-04-11 Elisabeth Dillies , Quentin Delfosse , Jannis Blüml , Raban Emunds , Florian Peter Busch , Kristian Kersting

Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…

Computation and Language · Computer Science 2024-04-05 Dawei Li , William Hogan , Jingbo Shang

Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if…

Artificial Intelligence · Computer Science 2025-11-18 Rhys Howard , Nick Hawes , Lars Kunze

Advances in large language models raise the question of how alignment techniques will adapt as models become increasingly complex and humans will only be able to supervise them weakly. Weak-to-Strong mimics such a scenario where weak model…

Computation and Language · Computer Science 2025-03-13 Ziyun Cui , Ziyang Zhang , Guangzhi Sun , Wen Wu , Chao Zhang

Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate writing reward models coarsely and fail to measure performance…

Computation and Language · Computer Science 2026-05-01 Qingyu Ren , Tianjun Pan , Xingzhou Chen , Xuhong Wang

As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue…

Artificial Intelligence · Computer Science 2026-02-10 Zehao Chen , Gongxun Li , Tianxiang Ai , Yifei Li , Zixuan Huang , Wang Zhou , Fuzhen Zhuang , Xianglong Liu , Jianxin Li , Deqing Wang , Yikun Ban

Causal representation learning has been proposed to encode relationships between factors presented in the high dimensional data. However, existing methods suffer from merely using a large amount of labeled data and ignore the fact that…

Machine Learning · Computer Science 2022-11-09 Jiageng Zhu , Hanchen Xie , Wael AbdAlmageed

The efficient exchange of information is an essential aspect of intelligent collective behavior. Event-triggered control and estimation achieve some efficiency by replacing continuous data exchange between agents with intermittent, or…

Systems and Control · Computer Science 2020-04-30 Friedrich Solowjow , Sebastian Trimpe

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…

Machine Learning · Computer Science 2025-02-26 Xuan He , Da Yin , Nanyun Peng

Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and…

Computation and Language · Computer Science 2021-05-11 Kung-Hsiang Huang , Nanyun Peng

Machine learning models have prevalent applications in many real-world problems, which increases the importance of correctness in the behaviour of these trained models. Finding a good test case that can reveal the potential failure in these…

Machine Learning · Computer Science 2022-06-14 Harsh Vardhan , Janos Sztipanovits

Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimation has traditionally served as the dominant training…

Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged…

Machine Learning · Computer Science 2024-07-18 Minh Hoang Nguyen , Hung Le , Svetha Venkatesh

Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An active community of researchers develops and enhances…

Artificial Intelligence · Computer Science 2019-11-05 Amanda Gentzel , Dan Garant , David Jensen

Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is…

Machine Learning · Computer Science 2025-02-17 Xueru Wen , Jie Lou , Yaojie Lu , Hongyu Lin , Xing Yu , Xinyu Lu , Ben He , Xianpei Han , Debing Zhang , Le Sun

The inaccessibility of controlled randomized trials due to inherent constraints in many fields of science has been a fundamental issue in causal inference. In this paper, we focus on distinguishing the cause from effect in the bivariate…

Machine Learning · Statistics 2021-02-23 Jean-Francois Ton , Dino Sejdinovic , Kenji Fukumizu

Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain many challenges: (1) Data scarcity. (2) Capturing the…

Computation and Language · Computer Science 2020-10-08 Jie Ma , Shuai Wang , Rishita Anubhai , Miguel Ballesteros , Yaser Al-Onaizan

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Eliciting knowledge from pre-trained language models via prompt-based learning has shown great potential in many natural language processing tasks. Whereas, the applications for more complex tasks such as event extraction are less studied…

Computation and Language · Computer Science 2022-05-16 Jiaju Lin , Qin Chen

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

Machine Learning · Computer Science 2018-03-14 Osbert Bastani , Carolyn Kim , Hamsa Bastani