9 papers
One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail
Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim +5
Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review. This decision is usual…
Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation
Zhaoyang Jiang, Zhizhong Fu, Zicheng Li +5
AI systems increasingly retrieve from records that revise themselves: issue threads, encyclopedic histories, policy logs, and long conversations. The challenge is not only finding…
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
Zhanchao Xu, Haoyang Li, Qingfa Xiao +4
Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, ove…
AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
Yubo Wang, Haoyang Li, Fei Teng +1
Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, ex…
GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification
Yubo Wang, Haoyang Li, Fei Teng +1
Text classification is vital for Web for Good applications like hate speech and misinformation detection. However, traditional models (e.g., BERT) often fail in dynamic few-shot se…
LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation
Fei Teng, Haoyang Li, Lei Chen
Modern computing systems, such as HDFS and Spark, produce vast quantities of logs that developers use for tasks like anomaly detection and error analysis. To simplify log analysis,…