相关论文: Training Stratigraphy: Persistent Behavioral Artif…

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…

Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance…

The use of reinforcement learning to dynamically adapt and evade detection is now well-documented in several cybersecurity settings including Covert Social Influence Operations (CSIOs), in which bots try to spread disinformation. While AI…

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

This paper argues that Large Language Models (LLMs) should incorporate explicit mechanisms for human empathy. As LLMs become increasingly deployed in high-stakes human-centered settings, their success depends not only on correctness or…

Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and…

Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing…

While multimodal large language models (MLLMs) have made substantial progress in single-image spatial reasoning, multi-image spatial reasoning, which requires integration of information from multiple viewpoints, remains challenging.…

Post-Traumatic Stress Disorder (PTSD) is fundamentally a neuroplastic problem traumatic contact events encode over-reactive neural pathways through Hebbian long-term potentiation, producing hair-triggered amygdala-HPA stress cascades that…

Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, and nonlinear geometry of model representations. We apply…

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Artificial Intelligence (AI) is increasingly being integrated into scientific research, particularly in the social sciences, where understanding human behavior is critical. Large Language Models (LLMs) have shown promise in replicating…

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the…

Accurately modeling detailed interactions between human/hand and object is an appealing yet challenging task. Current multi-view capture systems are only capable of reconstructing multiple subjects into a single, unified mesh, which fails…

This study introduces a novel method for revealing human internal attention patterns (decision-relevant attention) from gameplay data alone, leveraging offline attention techniques from reinforcement learning (RL). We propose…

Vision-language models are increasingly employed as multimodal conversational agents (MCAs) for diverse conversational tasks. Recently, reinforcement learning (RL) has been widely explored for adapting MCAs to various human-AI interaction…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human…

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models (LLMs) with human preferences, thereby enhancing the quality of responses generated. A critical component of RLHF is the reward model,…