Merging Generated and Retrieved Knowledge for Open-Domain QA
Zhang, Yunxiang, Khalifa, Muhammad, Logeswaran, Lajanugen, Lee, Moontae, Lee, Honglak, Wang, Lu
–arXiv.org Artificial Intelligence
Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage. Alternatively, prompting large language models (LLMs) to generate contextual passages based on their parametric knowledge has been shown to improve QA performance. Yet, LLMs tend to "hallucinate" content that conflicts with the retrieved knowledge. Based on the intuition that answers supported by both sources are more likely to be correct, we propose COMBO, a Compatibility-Oriented knowledge Merging for Better Open-domain QA framework, to effectively leverage the two sources of information. Concretely, we match LLM-generated passages with retrieved counterparts into compatible pairs, based on discriminators trained with silver compatibility labels. Then a Fusion-in-Decoder-based reader model handles passage pairs to arrive at the final answer. Experiments show that COMBO outperforms competitive baselines on three out of four tested open-domain QA benchmarks. Further analysis reveals that our proposed framework demonstrates greater efficacy in scenarios with a higher degree of knowledge conflicts.
arXiv.org Artificial Intelligence
Oct-22-2023
- Country:
- Oceania > Australia (0.04)
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.14)
- Texas > Travis County
- Austin (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Illinois > Cook County
- Chicago (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- Washington > King County
- Canada
- Ontario > Toronto (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Europe
- Austria (0.04)
- Switzerland > Zürich
- Zürich (0.14)
- Italy
- Tuscany > Florence (0.04)
- Calabria > Catanzaro Province
- Catanzaro (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- Japan (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- India > West Bengal
- Kolkata (0.04)
- Africa > Rwanda
- Genre:
- Research Report (0.82)
- Industry:
- Media > Television (0.68)
- Leisure & Entertainment > Sports
- Football (0.67)
- Technology: