7 papers
CodeScout: Contextual Problem Statement Enhancement for Software Agents
Manan Suri, Xiangci Li, Mehdi Shojaie +5
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of…
How Does Knowledge Selection Help Retrieval Augmented Generation?
Xiangci Li, Jessica Ouyang
Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model's output. While prior work has de…
Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branching
Xiangci Li, Zhiyu Chen, Jason Ingyu Choi +4
The goal of conversational product search (CPS) is to develop an intelligent, chat-based shopping assistant that can directly interact with customers to understand shopping intents…
Multi-round, Chain-of-thought Post-editing for Unfaithful Summaries
Yi-Hui Lee, Xiangci Li, Jessica Ouyang
Recent large language models (LLMs) have demonstrated a remarkable ability to perform natural language understanding and generation tasks. In this work, we investigate the use of L…
Improving Citation Text Generation: Overcoming Limitations in Length Control
Biswadip Mandal, Xiangci Li, Jessica Ouyang
A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior wo…
Minimal Evidence Group Identification for Claim Verification
Xiangci Li, Sihao Chen, Rajvi Kapadia +2
Claim verification in real-world settings (e.g. against a large collection of candidate evidences retrieved from the web) typically requires identifying and aggregating a complete…