Related papers: SPRInG: Continual LLM Personalization via Selectiv…

As personalized recommendation systems become vital in the age of information overload, traditional methods relying solely on historical user interactions often fail to fully capture the multifaceted nature of human interests. To enable…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…

Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adaptation to emerging…

Cross-Domain Sequential Recommendation (CDSR) aims to mine and transfer users' sequential preferences across different domains to alleviate the long-standing cold-start issue. Traditional CDSR models capture collaborative information…

Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content poses a significant challenge: While initial fine-tuning…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description…

The promise of generative AI to revolutionize education is constrained by the pedagogical limits of large language models (LLMs). A major issue is the lack of access to high-quality training data that reflect the learning of actual…

Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response aligns with a user's preferences, we argue that factuality is an…

The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic…

In modern commercial systems, including Recommendation, Ranking, and E-Commerce platforms, there is a trend towards improving customer experiences by incorporating Personalization context as input into Large Language Models (LLMs). However,…

Personalization in language models aims to tailor model behavior to individual users or user groups. Prompt-based methods incorporate user preferences into queries, while training-based methods encode them into model parameters. Model…

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

Large Language Models (LLMs), such as ChatGPT, exhibit advanced capabilities in generating text, images, and videos. However, their effective use remains constrained by challenges in prompt formulation, personalization, and opaque…

Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires developers to tailor a given code snippet in order to fit…

Strain sensors are gaining popularity in soft robotics for acquiring tactile data due to their flexibility and ease of integration. Tactile sensing plays a critical role in soft grippers, enabling them to safely interact with unstructured…

Recommender systems have traditionally followed modular architectures comprising candidate generation, multi-stage ranking, and re-ranking, each trained separately with supervised objectives and hand-engineered features. While effective in…

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…