4 papers
Proactive defense against LLM Jailbreak
Weiliang Zhao, Jinjun Peng, Daniel Ben-Levi +2
The proliferation of powerful large language models (LLMs) has necessitated robust safety alignment, yet these models remain vulnerable to evolving adversarial attacks, including m…
Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation
Ziwei Gong, Yanda Chen, Julia Hirschberg +4
Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that ar…
Business Logic-Driven Text-to-SQL Data Synthesis for Business Intelligence
Jinhui Liu, Ximeng Zhang, Yanbo Ai +1
Evaluating Text-to-SQL agents in private business intelligence (BI) settings is challenging due to the scarcity of realistic, domain-specific data. While synthetic evaluation data…
Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts
Kun Qian, Maximillian Chen, Siyan Li +2
Training conversational question-answering (QA) systems requires a substantial amount of in-domain data, which is often scarce in practice. A common solution to this challenge is t…