1 citations · 2 across the 13 of their papers we have counts for
7 papers · 1 filter
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Xinyang Liao, Lingyu Li, Kaicheng Shen +4
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely t…
Representational alignment yields generalizable safety in language models
Lingyu Li, Yan Teng, Yingchun Wang +1
Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet models remain vulnerable when the…
Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions
Kaicheng Shen, Lingyu Li, Wen Wu +3
AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over ti…
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
Xinyang Liao, Lingyu Li, Huacan Liu +5
As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Otherwise, such systems may rapidly…
Mechanistic Origin of Moral Indifference in Language Models
Lingyu Li, Yan Teng, Yingchun Wang
Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving L…
Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
Xiaoxing You, Qiang Huang, Lingyu Li +2
Multimodal Summarization (MMS) aims to generate concise textual summaries by understanding and integrating information across videos, transcripts, and images. However, existing app…
From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation
Tianle Gu, Kexin Huang, Lingyu Li +6
Safety moderation is pivotal for identifying harmful content. Despite the success of textual safety moderation, its multimodal counterparts remain hindered by a dual sparsity of da…