Related papers: G-Zero: Self-Play for Open-Ended Generation from Z…
Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry…
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…
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…
Detecting pre-training data in Large Language Models (LLMs) is crucial for auditing data privacy and copyright compliance, yet it remains challenging in black-box, zero-shot settings where computational resources and training data are…
Constructing robust simulators is essential for asking "what if?" questions and guiding policy in critical domains like healthcare and logistics. However, existing methods often struggle, either failing to generalize beyond historical data…
Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…
Emergent chain-of-thought (CoT) reasoning capabilities promise to improve performance and explainability of large language models (LLMs). However, uncertainties remain about how reasoning strategies formulated for previous model generations…
Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the…
Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational…
Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizing self-generated synthetic data has become crucial for…
Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that…
Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment,…
Recent years have witnessed a growing focus on automated software vulnerability detection. Notably, deep learning (DL)-based methods, which employ source code for the implicit acquisition of vulnerability patterns, have demonstrated…
Generative LLM-based recommenders (LLM-Rec) require continual post-deployment updates, yet deployment logs provide only policy-shaped contextual bandit feedback: outcomes are observed solely for items exposed by a prior serving policy,…
GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…
Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…
Recent Language Models (LMs) achieve breakthrough performance in code generation when trained on human-authored problems, even solving some competitive-programming problems. Self-play has proven useful in games such as Go, and thus it is…
Despite the growing use of large language models (LLMs) for providing feedback, limited research has explored how to achieve high-quality feedback. This case study introduces an evaluation framework to assess different zero-shot prompt…