English
Related papers

Related papers: Emergent Misalignment is Easy, Narrow Misalignment…

200 papers

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Machine Learning · Computer Science 2024-01-17 Houda Nait El Barj , Theophile Sautory

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

Computation and Language · Computer Science 2024-10-29 Sebastian Pineda Arango , Maciej Janowski , Lennart Purucker , Arber Zela , Frank Hutter , Josif Grabocka

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…

Computation and Language · Computer Science 2024-06-06 Peter Hase , Mohit Bansal , Peter Clark , Sarah Wiegreffe

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data…

Computation and Language · Computer Science 2025-01-16 Xinshuo Hu , Zifei Shan , Xinping Zhao , Zetian Sun , Zhenyu Liu , Dongfang Li , Shaolin Ye , Xinyuan Wei , Qian Chen , Baotian Hu , Haofen Wang , Jun Yu , Min Zhang

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either…

Machine Learning · Computer Science 2026-05-19 Yuhan Huang , Huanran Chen , Yinpeng Dong

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…

Computation and Language · Computer Science 2024-10-23 Benedict Aaron Tjandra , Muhammed Razzak , Jannik Kossen , Kunal Handa , Yarin Gal

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger

Latent variable models are a fundamental modeling tool in machine learning applications, but they present significant computational and analytical challenges. The popular EM algorithm and its variants, is a much used algorithmic tool; yet…

Machine Learning · Computer Science 2015-12-08 Xinyang Yi , Constantine Caramanis

Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…

Machine Learning · Computer Science 2025-03-04 Yan Scholten , Stephan Günnemann , Leo Schwinn

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

Artificial Intelligence · Computer Science 2025-08-08 Chang Tian , Matthew B. Blaschko , Mingzhe Xing , Xiuxing Li , Yinliang Yue , Marie-Francine Moens

Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty,…

Computation and Language · Computer Science 2024-06-12 Bairu Hou , Yujian Liu , Kaizhi Qian , Jacob Andreas , Shiyu Chang , Yang Zhang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on…

Machine Learning · Computer Science 2025-05-27 Zihan Guan , Mengxuan Hu , Ronghang Zhu , Sheng Li , Anil Vullikanti

Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often has high GPU memory usage, which makes it hard to use in settings with limited resources. To…

Machine Learning · Computer Science 2026-05-11 Zhishen Sun , Sizhe Dang , Guang Dai , Haishan Ye

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…

Computation and Language · Computer Science 2026-01-27 Linyang He , Tianjun Zhong , Richard Antonello , Gavin Mischler , Micah Goldblum , Nima Mesgarani

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Computation and Language · Computer Science 2025-09-16 Peter West , Christopher Potts

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Machine Learning · Computer Science 2025-07-30 Andrii Balashov

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang