Related papers: Internal Value Alignment in Large Language Models …

Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors…

Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies…

Large language models (LLMs) generate diverse, situated, persuasive texts from a plurality of potential perspectives, influenced heavily by their prompts and training data. As part of LLM adoption, we seek to characterize - and ideally,…

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies have investigated VLM personalization to understand user-provided concepts.…

In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be of low quality, hindering its effectiveness for real-world…

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a…

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

The synthesis of inductive loop invariants is a critical bottleneck in automated program verification. While Large Language Models (LLMs) show promise in mitigating this issue, they often fail on hard instances, generating invariants that…

With the rapid development of embodied artificial intelligence, significant progress has been made in vision-language-action (VLA) models for general robot decision-making. However, the majority of existing VLAs fail to account for the…

The assessment of advanced generative large language models (LLMs) poses a significant challenge, given their heightened complexity in recent developments. Furthermore, evaluating the performance of LLM-based applications in various…

The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS). However, as the number of agents increases, the issues of hallucination in LLMs…

Large language models often generate factually incorrect outputs, motivating efforts to detect the truthfulness of their content. Most existing approaches rely on training probes over internal activations, but these methods suffer from…

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Many NLP classification tasks, such as sexism/racism detection or toxicity detection, are based on human values. Yet, human values can vary under diverse cultural conditions. Therefore, we introduce a framework for value-aligned…

In modern dialogue systems, the use of Large Language Models (LLMs) has grown exponentially due to their capacity to generate diverse, relevant, and creative responses. Despite their strengths, striking a balance between the LLMs'…

Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of CAV often necessitates a large number of high-quality images,…

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

Values are core drivers of individual and collective perception, cognition, and behavior. Value systems, such as Schwartz's Theory of Basic Human Values, delineate the hierarchy and interplay among these values, enabling cross-disciplinary…

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

This paper introduces a novel approach to efficiently feeding knowledge to language models (LLMs) during prediction by integrating retrieval and generation processes within a unified framework. While the Retrieval-Augmented Generation (RAG)…