ArXiv TLDR

Xinyu Wang

4 papers · Latest:

Natural Language Processing

Emotion-Cause Pair Extraction in Conversations via Semantic Decoupling and Graph Alignment

SCALE disentangles emotion and cause semantics in conversations, using optimal transport for global emotion-cause pair extraction, achieving SOTA.

2604.19547
Natural Language Processing

Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation

This paper introduces MANYFAKE, a new benchmark for detecting subtle, strategically generated fake news, revealing current models struggle with mixed-truth content.

2604.09514

Silence and Noise: Self-censorship and Opinion Expression on Social Media

This paper explores self-censorship on social media, finding users in large, unsupportive communities often adjust or withhold opinions.

2604.09465
Machine Learning

Co-Evolution of Policy and Internal Reward for Language Agents

Self-Guide enables language agents to generate and refine internal rewards, improving policy optimization and inference-time guidance for long-horizon tasks.

2604.03098

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.