相关论文: Steering LLMs for Culturally Localized Generation

Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model (LLM) with a vision encoder. However, both the LLM and the…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Large Language Models have been widely been adopted by users for writing tasks such as sentence completions. While this can improve writing efficiency, prior research shows that LLM-generated suggestions may exhibit cultural biases which…

Autonomous navigation in unfamiliar environments often relies on geometric mapping and planning strategies that overlook rich semantic cues such as signs, room numbers, and textual labels. We propose a novel semantic navigation framework…

With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round self-improving methods allow LLMs to generate…

Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research focuses on interactions between a single LM and a single…

As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their users is essential for enhancing…

LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing…

A basic aspiration for interpretability research in large language models is to "localize" semantically meaningful behaviors to particular components within the LLM. There are various heuristics for finding candidate locations within the…

LLMs as intelligent agents are being increasingly applied in scenarios where human interactions are involved, leading to a critical concern about whether LLMs are faithful to the variations in culture across regions. Several works have…

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges. Current methods, such as Reinforcement Learning from Human Feedback…

Concepts benefit natural language understanding but are far from complete in existing knowledge graphs (KGs). Recently, pre-trained language models (PLMs) have been widely used in text-based concept extraction (CE). However, PLMs tend to…

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Large Language Models (LLMs) are widely used in Automated Essay Scoring (AES) due to their ability to capture semantic meaning. Traditional fine-tuning approaches required technical expertise, limiting accessibility for educators with…

Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

As large language models (LLMs) become widely deployed, concerns about their safety and alignment grow. An approach to steer LLM behavior, such as mitigating biases or defending against jailbreaks, is to identify which parts of a prompt…