English
Related papers

Related papers: Recontextualization Mitigates Specification Gaming…

200 papers

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

Reward functions, learned or manually specified, are rarely perfect. Instead of accurately expressing human goals, these reward functions are often distorted by human beliefs about how best to achieve those goals. Specifically, these reward…

Machine Learning · Computer Science 2025-07-16 Henrik Marklund , Alex Infanger , Benjamin Van Roy

Cognitive control, the ability of a system to adapt to the demands of a task, is an integral part of cognition. A widely accepted fact about cognitive control is that it is context-sensitive: Adults and children alike infer information…

Artificial Intelligence · Computer Science 2020-12-02 Rachit Dubey , Erin Grant , Michael Luo , Karthik Narasimhan , Thomas Griffiths

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a…

Machine Learning · Computer Science 2012-03-05 Alekh Agarwal , Miroslav Dudík , Satyen Kale , John Langford , Robert E. Schapire

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be…

The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues…

Computation and Language · Computer Science 2025-09-05 Charmaine Barker , Dimitar Kazakov

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Machine Learning · Computer Science 2026-03-03 Vivswan Shah , Randy Cogill , Hanwei Yue , Gopinath Chennupati , Rinat Khaziev

While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging: capability-oriented training induced exploitation. We investigate whether language models, when…

Machine Learning · Computer Science 2026-02-13 Yujun Zhou , Yue Huang , Han Bao , Kehan Guo , Zhenwen Liang , Pin-Yu Chen , Tian Gao , Werner Geyer , Nuno Moniz , Nitesh V Chawla , Xiangliang Zhang

Prompting Large Language Models (LLMs), or providing context on the expected model of operation, is an effective way to steer the outputs of such models to satisfy human desiderata after they have been trained. But in rapidly evolving…

Machine Learning · Computer Science 2025-08-08 Younwoo Choi , Muhammad Adil Asif , Ziwen Han , John Willes , Rahul G. Krishnan

Self-evaluation is increasingly central to language model training, underpinning techniques from Constitutional AI to self-refinement. We investigate whether coupling self-evaluation to reward signals creates incentives for wireheading,…

Artificial Intelligence · Computer Science 2025-12-02 David Demitri Africa , Hans Ethan Ting

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

Artificial Intelligence · Computer Science 2025-11-20 Alessio Pellegrino , Jacopo Mauro

This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding…

Machine Learning · Computer Science 2022-09-12 Frank Röder , Manfred Eppe , Stefan Wermter

In-context learning (ICL) is often motivated by the intuition that demonstrations help because they provide correct input-output examples. However, we reveal a counterintuitive phenomenon: correctness does not guarantee exemplar utility,…

Machine Learning · Computer Science 2026-05-27 Chenghao Qiu , Chunli Peng , Yufeng Yang , Kuan-Hao Huang , Yi Zhou

This chapter develops a unified framework for studying misspecified learning situations in which agents optimize and update beliefs within an incorrect model of their environment. We review the statistical foundations of learning from…

Theoretical Economics · Economics 2026-01-16 Ignacio Esponda , Demian Pouzo

We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…

Computation and Language · Computer Science 2020-09-16 Aran Komatsuzaki

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Computation and Language · Computer Science 2021-01-13 Evgeny Lagutin , Daniil Gavrilov , Pavel Kalaidin

Inverse reinforcement learning (IRL) aims to infer an agent's preferences (represented as a reward function $R$) from their behaviour (represented as a policy $\pi$). To do this, we need a behavioural model of how $\pi$ relates to $R$. In…

Machine Learning · Computer Science 2024-03-12 Joar Skalse , Alessandro Abate

Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve…

Computation and Language · Computer Science 2020-10-07 Shaoxiong Feng , Xuancheng Ren , Hongshen Chen , Bin Sun , Kan Li , Xu Sun

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton