Related papers: Prompt-Level Reward Specifications for Open-Ended …

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and…

The main challenge in developing effective reinforcement learning (RL) pipelines is often the design and tuning the reward functions. Well-designed shaping reward can lead to significantly faster learning. Naively formulated rewards,…

Pre-training models have shown their power in sequential recommendation. Recently, prompt has been widely explored and verified for tuning in NLP pre-training, which could help to more effectively and efficiently extract useful knowledge…

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Automated explanatory feedback systems play a crucial role in facilitating learning for a large cohort of learners by offering feedback that incorporates explanations, significantly enhancing the learning process. However, delivering such…

We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting…

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,…

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but…

Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications.…

Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…

Reward models are critical in techniques like Reinforcement Learning from Human Feedback (RLHF) and Inference Scaling Laws, where they guide language model alignment and select optimal responses. Despite their importance, existing reward…

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost…

Requirements classification assigns natural language requirements to predefined classes, such as functional and non functional. Accurate classification reduces risk and improves software quality. Most existing models rely on supervised…

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-standard approach is to run a full RLHF training pipeline and…