相关论文: Decoding Alignment: A Critical Survey of LLM Devel…

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

The advent of AI driven large language models (LLMs) have stirred discussions about their role in qualitative research. Some view these as tools to enrich human understanding, while others perceive them as threats to the core values of the…

Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align…

This paper presents the first systematic measurement of educational alignment in Large Language Models. Using a Delphi-validated instrument comprising 48 items across eight educational-theoretical dimensions, the study reveals that GPT-5.1…

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in improving LLM capabilities, its implementation remains highly…

Recent advancements in large language models (LLMs) have revitalized philosophical debates surrounding artificial intelligence. Two of the most fundamental challenges - namely, the Frame Problem and the Symbol Grounding Problem - have…

With the rapid advancement of AI, software engineering increasingly relies on AI-driven approaches, particularly language models (LMs), to enhance code performance. However, the trustworthiness and reliability of LMs remain significant…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, while integrating human feedback to enhance…

The advancement of large language models (LLMs) has outpaced traditional evaluation methodologies. This progress presents novel challenges, such as measuring human-like psychological constructs, moving beyond static and task-specific…

Computer programming (coding) is indispensable for researchers across disciplines, yet it remains challenging to learn and time-consuming to carry out. Generative AI, particularly large language models (LLMs), has the potential to transform…

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…

This paper explores the potential of large language models (LLMs) as reliable analytical tools in linguistic research, focusing on the emergence of affective meanings in temporal expressions involving manner-of-motion verbs. While LLMs like…

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework…

As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge.…

Multimodal Large Language Models (MLLMs) are widely regarded as crucial in the exploration of Artificial General Intelligence (AGI). The core of MLLMs lies in their capability to achieve cross-modal alignment. To attain this goal, current…

As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…

The ongoing evolution of AI paradigms has propelled AI research into the agentic AI stage. Consequently, the focus of research has shifted from single agents and simple applications towards multi-agent autonomous decision-making and task…