相关论文: Questioning the Survey Responses of Large Language…

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…

Large language models implicitly encode preferences over human values, yet steering them often requires large training data. In this work, we investigate a simple approach: Can we reliably modify a model's value system in downstream…

Topic models are used to make sense of large text collections. However, automatically evaluating topic model output and determining the optimal number of topics both have been longstanding challenges, with no effective automated solutions…

Large language models (LLMs) closely interact with humans, and thus need an intimate understanding of the cultural values of human society. In this paper, we explore how open-source LLMs make judgments on diverse categories of cultural…

Large Language Models (LLMs) have shown strong performance across many tasks, but their ability to capture culturally diverse moral values remains unclear. In this paper, we examine whether LLMs mirror variations in moral attitudes reported…

When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make predictions about upcoming words, has motivated their use as…

Research on the 'cultural alignment' of Large Language Models (LLMs) has emerged in response to growing interest in understanding representation across diverse stakeholders. Current approaches to evaluating cultural alignment through…

Large language models (LLMs) are increasingly used to simulate human opinions and survey responses, but their ability to reproduce population responses across cultures remains limited. Existing persona-based prompting methods typically rely…

To improve the reasoning and question-answering capabilities of Large Language Models (LLMs), several multi-agent approaches have been introduced. While these methods enhance performance, the application of collective intelligence-based…

The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…

The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a…

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar…

Sentiment analysis is one of the most widely used techniques in text analysis. Recent advancements with Large Language Models have made it more accurate and accessible than ever, allowing researchers to classify text with only a plain…

With the growing deployment of large language models (LLMs) across various applications, assessing the influence of gender biases embedded in LLMs becomes crucial. The topic of gender bias within the realm of natural language processing…

Large Language Models (LLMs) have demonstrated remarkable capabilities in executing tasks based on natural language queries. However, these models, trained on curated datasets, inherently embody biases ranging from racial to national and…

Languages typically provide more than one grammatical construction to express certain types of messages. A speaker's choice of construction is known to depend on multiple factors, including the choice of main verb -- a phenomenon known as…

Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In humans, such inputs influence judgments in ways that depend…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…

Question-answering (QA) and reading comprehension (RC) benchmarks are commonly used for assessing the capabilities of large language models (LLMs) to retrieve and reproduce knowledge. However, we demonstrate that popular QA and RC…

Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions,…