English
Related papers

Related papers: The Alignment Auditor: A Bayesian Framework for Ve…

200 papers

Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However, existing theories do not provide strong justification for…

Machine Learning · Computer Science 2026-05-19 Jihun Yun , Juno Kim , Jongho Park , Junhyuck Kim , Jongha Jon Ryu , Jaewoong Cho , Kwang-Sung Jun

Automated malware classification has achieved strong detection performance. Yet, malware behavior auditing seeks causal and verifiable explanations of malicious activities -- essential not only to reveal what malware does but also to…

Cryptography and Security · Computer Science 2025-09-19 Xinran Zheng , Xingzhi Qian , Yiling He , Shuo Yang , Lorenzo Cavallaro

Existing approaches to bias evaluation in large language models (LLMs) trade ecological validity for statistical control, relying either on artificial prompts that poorly reflect real-world use or on naturalistic tasks that lack scale and…

Computation and Language · Computer Science 2026-05-12 Akram Elbouanani , Aboubacar Tuo , Adrian Popescu

Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show…

Computation and Language · Computer Science 2024-11-04 Michal Lukasik , Harikrishna Narasimhan , Aditya Krishna Menon , Felix Yu , Sanjiv Kumar

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Inverse reinforcement learning (IRL) is the problem of inferring a reward function from expert behavior. There are several approaches to IRL, but most are designed to learn a Markovian reward. However, a reward function might be…

Machine Learning · Computer Science 2024-06-21 Noah Topper , Alvaro Velasquez , George Atia

Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding model competence). Current LLMs often conflate these…

Computation and Language · Computer Science 2026-02-03 Dengyun Peng , Qiguang Chen , Bofei Liu , Jiannan Guan , Libo Qin , Zheng Yan , Jinhao Liu , Jianshu Zhang , Wanxiang Che

Large language model (LLM) alignment relies on complex reward signals that often obscure the specific behaviors being incentivized, creating critical risks of misalignment and reward hacking. Existing interpretation methods typically rely…

Machine Learning · Computer Science 2026-05-22 Edward Chen , Sanmi Koyejo , Carlos Guestrin

Machine learning (ML) models often exhibit bias that can exacerbate inequities in biomedical applications. Fairness auditing, the process of evaluating a model's performance across subpopulations, is critical for identifying and mitigating…

Methodology · Statistics 2026-05-19 Jianhui Gao , Jessica Gronsbell

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

Machine Learning · Computer Science 2025-10-02 Yiran Shen , Yu Xia , Jonathan Chang , Prithviraj Ammanabrolu

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement…

Robotics · Computer Science 2025-09-12 Yongkai Tian , Yirong Qi , Xin Yu , Wenjun Wu , Jie Luo

Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, but often exhibit overconfidence and generate plausible yet incorrect answers. This overconfidence, especially in models undergone…

Computation and Language · Computer Science 2025-12-24 Zeguan Xiao , Diyang Dou , Boya Xiong , Yun Chen , Guanhua Chen

Financial statement auditing is essential for stakeholders to understand a company's financial health, yet current manual processes are inefficient and error-prone. Even with extensive verification procedures, auditors frequently miss…

Information Retrieval · Computer Science 2025-06-24 Rushi Wang , Jiateng Liu , Weijie Zhao , Shenglan Li , Denghui Zhang

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

Computation and Language · Computer Science 2025-06-02 Xiaoqing Cheng , Ruizhe Chen , Hongying Zan , Yuxiang Jia , Min Peng

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…

Artificial Intelligence · Computer Science 2026-01-01 Ananth Hariharan , Vardhan Dongre , Dilek Hakkani-Tür , Gokhan Tur

The imperative to eliminate undesirable data memorization underscores the significance of machine unlearning for large language models (LLMs). Recent research has introduced a series of promising unlearning methods, notably boosting the…

Machine Learning · Computer Science 2025-02-26 Qizhou Wang , Bo Han , Puning Yang , Jianing Zhu , Tongliang Liu , Masashi Sugiyama

Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges induce bias in naive evaluation scores. We propose a simple…

Machine Learning · Computer Science 2026-02-10 Chungpa Lee , Thomas Zeng , Jongwon Jeong , Jy-yong Sohn , Kangwook Lee

While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking ground-truth verifiers, such as LLM alignment. In this work, we…

Computation and Language · Computer Science 2026-02-20 Kejian Shi , Yixin Liu , Peifeng Wang , Alexander R. Fabbri , Shafiq Joty , Arman Cohan

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many…

Machine Learning · Computer Science 2024-03-15 Edward J. Hu , Moksh Jain , Eric Elmoznino , Younesse Kaddar , Guillaume Lajoie , Yoshua Bengio , Nikolay Malkin