English
Related papers

Related papers: Monitoring Emergent Reward Hacking During Generati…

200 papers

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

Computation and Language · Computer Science 2026-01-27 Jan Betley , Daniel Tan , Niels Warncke , Anna Sztyber-Betley , Xuchan Bao , Martín Soto , Nathan Labenz , Owain Evans

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

Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptation as alignment objectives and reward targets evolve. Existing theoretical analyses justify…

Machine Learning · Computer Science 2026-05-14 Ye Wang , Jing Liu , Toshiaki Koike-Akino

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Artificial Intelligence · Computer Science 2025-08-12 Annie Wong , Thomas Bäck , Aske Plaat , Niki van Stein , Anna V. Kononova

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…

Machine Learning · Computer Science 2025-11-04 Pouya M. Ghari , Simone Sciabola , Ye Wang

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Artificial Intelligence · Computer Science 2025-04-18 Andrew Kiruluta , Andreas Lemos , Priscilla Burity

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

In many RL applications, once training ends, it is vital to detect any deterioration in the agent performance as soon as possible. Furthermore, it often has to be done without modifying the policy and under minimal assumptions regarding the…

Machine Learning · Computer Science 2021-11-01 Ido Greenberg , Shie Mannor

Learning in artificial neural networks usually relies on continuous, externally driven weight updates, in which parameters are modified at every step in response to incoming data, error signals or reward feedback. In this setting, routine…

Neurons and Cognition · Quantitative Biology 2026-05-13 Arturo Tozzi

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…

Machine Learning · Computer Science 2026-05-12 Rohit Agarwal , Joshua Lin , Mark Braverman , Elad Hazan

The reward signal plays a central role in defining the desired behaviors of agents in reinforcement learning (RL). Rewards collected from realistic environments could be perturbed, corrupted, or noisy due to an adversary, sensor error, or…

Machine Learning · Computer Science 2025-03-12 Xi Chen , Zhihui Zhu , Andrew Perrault

Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards…

Artificial Intelligence · Computer Science 2025-07-29 Leonardo Villalobos-Arias , Grant Forbes , Jianxun Wang , David L Roberts , Arnav Jhala

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Artificial Intelligence · Computer Science 2024-11-01 Debangshu Banerjee , Aditya Gopalan

Latent learning, classically theorized by Tolman, shows that biological agents (e.g., rats) can acquire internal representations of their environment without rewards, enabling rapid adaptation once rewards are introduced. In contrast, from…

Machine Learning · Computer Science 2026-02-02 Jian Xiong , Jingbo Zhou , Zihan Zhou , Yixiong Xiao , Le Zhang , Jingyong Ye , Rui Qian , Yang Zhou , Dejing Dou

We present a method for active inference with partial observations in stochastic systems through incentive design, also known as the leader-follower game. Consider a leader agent who aims to infer a follower agent's type given a finite set…

Systems and Control · Electrical Eng. & Systems 2025-02-12 Xinyi Wei , Chongyang Shi , Shuo Han , Ahmed H. Hemida , Charles A. Kamhoua , Jie Fu

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Minbyul Jeong , Jaewoo Kang

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Artificial Intelligence · Computer Science 2025-02-28 Wei Xiong , Hanning Zhang , Chenlu Ye , Lichang Chen , Nan Jiang , Tong Zhang

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

Computation and Language · Computer Science 2025-10-06 Sebastian Gehrmann

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

Computation and Language · Computer Science 2023-12-14 Michael Noukhovitch , Samuel Lavoie , Florian Strub , Aaron Courville

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…

Artificial Intelligence · Computer Science 2026-05-28 Zhipeng Qian , Zihan Liang , Yufei Ma , Ben Chen , Huangyu Dai , Jiayi Ji , Chenyi Lei , Wenwu Ou , Xiaoshuai Sun , Qibin Hou