English
Related papers

Related papers: On the Sensitivity of Reward Inference to Misspeci…

200 papers

Model alignment is currently applied in a vacuum, evaluated primarily through standardised benchmark performance. The purpose of this study is to examine the effects of alignment on populations of models through time. We focus on the…

Artificial Intelligence · Computer Science 2026-04-08 Jonathan Elsworth Eicher

One of the most crucial issues in data mining is to model human behaviour in order to provide personalisation, adaptation and recommendation. This usually involves implicit or explicit knowledge, either by observing user interactions, or by…

Human-Computer Interaction · Computer Science 2017-08-21 Kevin Jasberg , Sergej Sizov

Language model alignment research often attempts to ensure that models are not only helpful and harmless, but also truthful and unbiased. However, optimizing these objectives simultaneously can obscure how improving one aspect might impact…

Computation and Language · Computer Science 2024-12-02 Suyash Fulay , William Brannon , Shrestha Mohanty , Cassandra Overney , Elinor Poole-Dayan , Deb Roy , Jad Kabbara

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…

Computation and Language · Computer Science 2022-12-13 Md Sultan Al Nahian , Spencer Frazier , Brent Harrison , Mark Riedl

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Machine Learning · Computer Science 2024-08-08 Shawn Im , Yixuan Li

We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g.,…

Robotics · Computer Science 2024-08-13 Connor Mattson , Anurag Aribandi , Daniel S. Brown

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation…

Machine Learning · Computer Science 2024-10-17 Rui Yang , Xiaoman Pan , Feng Luo , Shuang Qiu , Han Zhong , Dong Yu , Jianshu Chen

To make informed decisions in natural environments that change over time, humans must update their beliefs as new observations are gathered. Studies exploring human inference as a dynamical process that unfolds in time have focused on…

Neurons and Cognition · Quantitative Biology 2022-03-03 Arthur Prat-Carrabin , Robert C. Wilson , Jonathan D. Cohen , Rava Azeredo da Silveira

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

Reward models (RMs), which are central to existing post-training methods, aim to align LLM outputs with human values by providing feedback signals during fine-tuning. However, existing RMs struggle to capture nuanced, user-specific…

Machine Learning · Computer Science 2025-08-21 Mengdi Li , Guanqiao Chen , Xufeng Zhao , Haochen Wen , Shu Yang , Di Wang

There has been much recent interest in evaluating large language models for uncertainty calibration to facilitate model control and modulate user trust. Inference time uncertainty, which may provide a real-time signal to the model or…

Computation and Language · Computer Science 2025-08-12 Kyle Moore , Jesse Roberts , Daryl Watson

An important use of machine learning is to learn what people value. What posts or photos should a user be shown? Which jobs or activities would a person find rewarding? In each case, observations of people's past choices can inform our…

Artificial Intelligence · Computer Science 2015-12-21 Owain Evans , Andreas Stuhlmueller , Noah D. Goodman

In many real-world applications, the reward function is too complex to be manually specified. In such cases, reward functions must instead be learned from human feedback. Since the learned reward may fail to represent user preferences, it…

Machine Learning · Computer Science 2022-03-28 Erik Jenner , Adam Gleave

Reward models are critical in techniques like Reinforcement Learning from Human Feedback (RLHF) and Inference Scaling Laws, where they guide language model alignment and select optimal responses. Despite their importance, existing reward…

Computation and Language · Computer Science 2024-10-22 Yantao Liu , Zijun Yao , Rui Min , Yixin Cao , Lei Hou , Juanzi Li

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

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Machine Learning · Computer Science 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor

Explanations are hypothesized to improve human understanding of machine learning models and achieve a variety of desirable outcomes, ranging from model debugging to enhancing human decision making. However, empirical studies have found…

Artificial Intelligence · Computer Science 2023-05-02 Chacha Chen , Shi Feng , Amit Sharma , Chenhao Tan

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Computation and Language · Computer Science 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo

A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this…

Computation and Language · Computer Science 2024-07-22 Zihao Wang , Chirag Nagpal , Jonathan Berant , Jacob Eisenstein , Alex D'Amour , Sanmi Koyejo , Victor Veitch

A myriad of explainability methods have been proposed in recent years, but there is little consensus on how to evaluate them. While automatic metrics allow for quick benchmarking, it isn't clear how such metrics reflect human interaction…

Computation and Language · Computer Science 2021-06-30 Ana Valeria Gonzalez , Anna Rogers , Anders Søgaard
‹ Prev 1 8 9 10 Next ›