Related papers: One fish, two fish, but not the whole sea: Alignme…

What role can the otherwise successful Large Language Models (LLMs) play in the understanding of human cognition, and in particular in terms of informing language acquisition debates? To contribute to this question, we first argue that…

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…

The alignment process changes several properties of a large language model's (LLM's) output distribution. We analyze two aspects of post-alignment distributional shift of LLM responses. First, we re-examine previously reported reductions in…

Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We first…

Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotators' different…

This study explores the potential of large language models (LLMs) to conduct market experiments, aiming to understand their capability to comprehend competitive market dynamics. We model the behavior of market agents in a controlled…

Large language models (LLMs) are increasing in capability and popularity, propelling their application in new domains -- including as replacements for human participants in computational social science, user testing, annotation tasks, and…

The intricate relationship between language and culture has long been a subject of exploration within the realm of linguistic anthropology. Large Language Models (LLMs), promoted as repositories of collective human knowledge, raise a…

Large language models (LLMs) are increasingly used to simulate human behavior in social settings such as legal mediation, negotiation, and dispute resolution. However, it remains unclear whether these simulations reproduce the…

Recent work suggests that preference-tuning techniques -- such as Reinforcement Learning from Human Feedback (RLHF) methods like PPO and GRPO, as well as alternatives like DPO -- reduce diversity, creating a dilemma given that these models…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research…

Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether…

Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous studies have revealed the misalignment of LLMs with human…

The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models…

The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly…

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that…

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant…

The trustworthiness of Large Language Models (LLMs) refers to the extent to which their outputs are reliable, safe, and ethically aligned, and it has become a crucial consideration alongside their cognitive performance. In practice,…