Related papers: FunPRM: Function-as-Step Process Reward Model with…

In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high incidence of false positives-solutions that reach the…

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation…

Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform…

Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to…

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…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length…

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and…

Code generation problems differ from common natural language problems - they require matching the exact syntax of the target language, identifying happy paths and edge cases, paying attention to numerous small details in the problem spec,…

Automating radiology report generation with Large Vision-Language Models (LVLMs) holds great potential, yet these models often produce clinically critical hallucinations, posing serious risks. Existing hallucination detection methods…

Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question…

Recent studies on post-training large language models (LLMs) for reasoning through reinforcement learning (RL) typically focus on tasks that can be accurately verified and rewarded, such as solving math problems. In contrast, our research…

Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…

Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling…

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Large Language Models (LLMs) can generate plausible code, but in settings that require exact stdin/stdout behavior they frequently produce programs that compile yet fail tests, and in some cases they introduce security-sensitive patterns.…

Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Estimation (MCE), defines process rewards as the probability…