ArXiv TLDR

Chonglin Sun

2 papers · Latest:

Natural Language Processing

Learning Evidence Highlighting for Frozen LLMs

HiLight is a framework that trains a lightweight actor to highlight key evidence in long contexts for frozen LLMs, improving reasoning without modifying the LLM.

2604.22565
Information Retrieval

Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation

This paper proposes a hierarchical indexing method using cross-attention and residual quantization to efficiently scale large-scale retrieval models for recommendations.

2604.12965

📬 Weekly AI Paper Digest

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