Related papers: Align$^3$GR: Unified Multi-Level Alignment for LLM…
Large language models (LLMs) are still struggling in aligning with human preference in complex tasks and scenarios. They are prone to overfit into the unexpected patterns or superficial styles in the training data. We conduct an empirical…
Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to…
In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these recommendations heavily rely on historical search logs to…
The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…
Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity…
Large language model (LLM)-enhanced sequential recommendation typically aims to improve two core components: user semantic embedding extraction and utilization. Despite promising results, existing methods still have two limitations: 1) In…
LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…
With the rapid growth of fintech, personalized financial product recommendations have become increasingly important. Traditional methods like collaborative filtering or content-based models often fail to capture users' latent preferences…
Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often…
Sequential recommendation systems aim to predict users' next likely interaction based on their history. However, these systems face data sparsity and cold-start problems. Utilizing data from other domains, known as multi-domain methods, is…
Do current large language models (LLMs) better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation…
Large language models (LLMs) have been widely adopted to enrich the semantic representation of textual item information in recommender systems. However, existing linear autoencoders (LAEs) that incorporate textual information rely on sparse…
The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper…
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous. To improve…
Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…
Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this…
Large language models (LLMs) have not only revolutionized the field of natural language processing (NLP) but also have the potential to bring a paradigm shift in many other fields due to their remarkable abilities of language understanding,…
Personalizing large language models (LLMs) is important for aligning outputs with diverse user preferences, yet existing methods struggle with flexibility and generalization. We propose CoPL (Collaborative Preference Learning), a…
Traditional recommender systems such as matrix factorization methods have primarily focused on learning a shared dense embedding space to represent both items and user preferences. Subsequently, sequence models such as RNN, GRUs, and,…
Modeling user preferences across domains remains a key challenge in slate recommendation (i.e. recommending an ordered sequence of items) research. We investigate how Large Language Models (LLM) can effectively act as world models of user…