Related papers: SafeCRS: Personalized Safety Alignment for LLM-Bas…

Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due…

In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic focused services. To better accomplish this task, conversational recommendation systems (CRS)…

Conversational Recommender Systems (CRS) actively elicit user preferences to generate adaptive recommendations. Mainstream reinforcement learning-based CRS solutions heavily rely on handcrafted reward functions, which may not be aligned…

Conversational Recommender Systems (CRSs) are receiving growing research attention across domains, yet their user experience (UX) evaluation remains limited. Existing reviews largely overlook empirical UX studies, particularly in adaptive…

Conversational Recommender Systems (CRSs)aim to engage users in dialogue to provide tailored recommendations. While traditional CRSs focus on eliciting preferences and retrieving items, real-world e-commerce interactions involve more…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

We tackle the challenge of integrating large language models (LLMs) with external recommender systems to enhance domain expertise in conversational recommendation (CRS). Current LLM-based CRS approaches primarily rely on zero/few-shot…

The successful integration of large language models (LLMs) into recommendation systems has proven to be a major breakthrough in recent studies, paving the way for more generic and transferable recommendations. However, LLMs struggle to…

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

Conversational Recommender Systems (CRSs) have attracted growing attention for their ability to deliver personalized recommendations through natural language interactions. To more accurately infer user preferences from multi-turn…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Research and development on conversational recommender systems (CRSs) critically depends on sound and reliable evaluation methodologies. However, the interactive nature of these systems poses significant challenges for automatic evaluation.…

We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…

Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations. To develop an effective CRS, high-quality CRS datasets are very crucial. However, existing CRS datasets suffer from the…

Large language models (LLMs) typically generate identical or similar responses for all users given the same prompt, posing serious safety risks in high-stakes applications where user vulnerabilities differ widely. Existing safety…

Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to…

Conversational recommender systems (CRS) dynamically obtain the user preferences via multi-turn questions and answers. The existing CRS solutions are widely dominated by deep reinforcement learning algorithms. However, deep reinforcement…

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…