Related papers: Can an LLM Learn Preferences from Choice Data?

Large Language Models (LLMs) are being increasingly explored as general-purpose tools for recommendation tasks, enabling zero-shot and instruction-following capabilities without the need for task-specific training. While the research…

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important…

Previous work has showcased the intriguing capabilities of Large Language Models (LLMs) in instruction-following and rhetorical fluency. However, systematic exploration of their dual capabilities to autonomously persuade and resist…

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains…

Large language models (LLMs) must often respond to highly ambiguous user requests. In such cases, the LLM's best response may be to ask a clarifying question to elicit more information. Existing LLMs often respond by presupposing a single…

While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This…

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…

The paper underscores the significance of Large Language Models (LLMs) in reshaping recommender systems, attributing their value to unique reasoning abilities absent in traditional recommenders. Unlike conventional systems lacking direct…

What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approaches largely rely on binary pairwise comparisons, overlooking…

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in choosing which goals to pursue, rather than completing predefined tasks. However, the assumption…

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

We investigate the choice patterns of Large Language Models (LLMs) in the context of Decisions from Experience tasks that involve repeated choice and learning from feedback, and compare their behavior to human participants. We find that on…

Recent preference learning frameworks for large language models (LLMs) simplify human preferences with binary pairwise comparisons and scalar rewards. This simplification could make LLMs' responses biased to mostly preferred features, and…

LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey why users prefer responses that are chosen or rejected, so LLMs trained on these…

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or…

Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…

Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks due to the difficulty in designing comprehensive and precise reward functions. This inherent difficulty curtails the broader…