6 papers
MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents
Jiaming Chen, Yisen Gao, Yanping Li +3
Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for malicious records, making th…
TACO: Task-Aware Column Description Generation Using LLMs
Ting Cai, Rakesh R. Menon, Yiru Chen +8
Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks…
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu +7
Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision.…
ISEE: Interactive Semantic Enrichment for Database Fields
Yuan Tian, Yiru Chen, Rakesh R. Menon +8
LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their performance heavily depends on the…
ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
John Murzaku, Zifan Liu, Vaishnavi Muppala +3
Large language models (LLMs) have shown remarkable progress in understanding and generating natural language across various applications. However, they often struggle with resolvin…
ECLAIR: Enhanced Clarification for Interactive Responses
John Murzaku, Zifan Liu, Md Mehrab Tanjim +3
We present ECLAIR (Enhanced CLArification for Interactive Responses), a novel unified and end-to-end framework for interactive disambiguation in enterprise AI assistants. ECLAIR ge…