相关论文: Diagnosing Training Inference Mismatch in LLM Rein…

Backdoor attacks typically place a specific trigger on certain training data, such that the model makes prediction errors on inputs with that trigger during inference. Despite the core role of the trigger, existing studies have commonly…

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a…

A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…

Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, where the distribution of classes…

Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical evaluation on over 350…

While Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse tasks, their practical deployment is severely hindered by hallucination issues, which become particularly acute during Reinforcement Learning…

Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. However, a single average performance score on the entire test set is inadequate in determining such…

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

As large language models (LLMs) become widespread in various application domains, a critical challenge the AI community is facing is how to train these large AI models in a cost-effective manner. Existing LLM training plans typically employ…

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Large language model (LLM)-enhanced recommendation models inject LLM representations into backbone recommenders to exploit rich item text without inference-time LLM cost. However, we find that existing LLM-enhanced methods significantly…