DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness
By: Jiabao Ji , Min Li , Priyanshu Kumar and more
Potential Business Impact:
Helps computers answer tricky questions better.
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as Which actor from the film Heat won at least one Academy Award?, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA benchmarks rarely evaluate both challenges jointly. To address this, we introduce DeepAmbigQAGen, an automatic data generation pipeline that constructs QA tasks grounded in text corpora and linked knowledge graph, generating natural and verifiable questions that systematically embed name ambiguity and multi-step reasoning. Based on this, we build DeepAmbigQA, a dataset of 3,600 questions requiring multi-hop reasoning and half of them explicit name ambiguity resolving. Experiments reveal that, even state-of-the-art GPT-5 show incomplete answers, achieving only 0.13 exact match on ambiguous questions and 0.21 on non-ambiguous questions. These findings highlight the need for more robust QA systems aimed at information gathering and answer completeness.
Similar Papers
A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
Computation and Language
Helps computers answer questions with many right answers.
BMGQ: A Bottom-up Method for Generating Complex Multi-hop Reasoning Questions from Semi-structured Data
Artificial Intelligence
Makes computers better at answering tricky questions.
Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey
Computation and Language
Helps computers understand confusing words better.