Related papers: Aligning LLM Agents by Learning Latent Preference …
Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…
Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…
Large language model-based agents are becoming increasingly popular as a low-cost mechanism to provide personalized, conversational advice, and have demonstrated impressive capabilities in relatively simple scenarios, such as movie…
Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…
User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms…
Large language models (LLMs) have shown that generative pretraining can distill vast world knowledge into compact token representations. While LLMs encapsulate extensive world knowledge, they remain limited in modeling the behavioral…
Conversational recommender systems (CRS) based on Large Language Models (LLMs) need to constantly be aligned to the user preferences to provide satisfying and context-relevant item recommendations. The traditional supervised fine-tuning…
Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or…
While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an…
Interactive recommender systems can dynamically adapt to user feedback, but often suffer from content homogeneity and filter bubble effects due to overfitting short-term user preferences. While recent efforts aim to improve content…
Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implicitly treats preference as static, even though many…
Accurately modeling user preferences is crucial for improving the performance of content-based recommender systems. Existing approaches often rely on simplistic user profiling methods, such as averaging or concatenating item embeddings,…
The rapid advancement of large language models (LLMs) has led to the widespread adoption of AI-powered coding assistants integrated into a development environment. On one hand, low-latency code completion offers completion suggestions but…
This paper argues that large language model-based recommenders can displace today's attention-allocation machinery. LLM-based recommenders would ingest open-web content, infer a user's natural-language goals, and present information that…
Many real-world tasks, such as trip planning or meal planning, can be formulated as combinatorial optimization problems. However, using optimization solvers is difficult for end users because it requires problem instantiation: defining…
Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…
We present Mem-$\pi$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on…
Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…
The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet,…
Recommender systems are indispensable in the realm of online applications, and sequential recommendation has enjoyed considerable prevalence due to its capacity to encapsulate the dynamic shifts in user interests. However, previous…