相关论文: Does Self-Evaluation Enable Wireheading in Languag…

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit…

Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms (Yuan et al., 2024) have shown that LLMs can…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this…

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

Significant progress in reward modeling over recent years has been driven by a paradigm shift from task-specific designs towards generalist reward models. Despite this trend, developing effective reward models remains a fundamental…

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…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human users, a second language model can be used as an evaluator,…

Mixed incentives among a population with multiagent teams has been shown to have advantages over a fully cooperative system; however, discovering the best mixture of incentives or team structure is a difficult and dynamic problem. We…

Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a…

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…

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…

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses,…

Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or scalar reward models) to produce reward signals. Each…