Retrieving Supporting Evidence for Generative Question Answering
| dc.contributor.author | Huo, Siqing | |
| dc.date.accessioned | 2023-12-18T20:54:29Z | |
| dc.date.available | 2023-12-18T20:54:29Z | |
| dc.date.issued | 2023-12-18 | |
| dc.date.submitted | 2023-12-14 | |
| dc.description.abstract | Current large language models (LLMs) can exhibit near-human levels of performance on many natural language-based tasks, including open-domain question answering. Unfortunately, at this time, they also convincingly hallucinate incorrect answers, so that responses to questions must be verified against external sources before they can be accepted at face value. In the thesis, I report two simple experiments to automatically validate generated answers against a corpus. We base our experiments on questions and passages from the MS MARCO (V1) test collection, and a retrieval pipeline consisting of sparse retrieval, dense retrieval and neural rerankers. In the first experiment, we validate the generated answer in its entirety. After presenting a question to an LLM and receiving a generated answer, we query the corpus with the combination of the question + generated answer. We then present the LLM with the combination of the question + generated answer + retrieved answer, prompting it to indicate if the generated answer can be supported by the retrieved answer. In the second experiment, we consider the generated answer at a more granular level, prompting the LLM to extract a list of factual statements from the answer and verifying each statement separately. We query the corpus with each factual statement and then present the LLM with the statement and the corresponding retrieved evidence. The LLM is prompted to indicate if the statement can be supported and make necessary edits using the retrieved material. With an accuracy of over 80%, we find that an LLM is capable of verifying its generated answer when a corpus of supporting material is provided. However, manual assessment of a random sample of questions reveals that incorrect generated answers are missed by this verification process. While this verification process can reduce hallucinations, it can not entirely eliminate them. | en |
| dc.identifier.uri | http://hdl.handle.net/10012/20174 | |
| dc.language.iso | en | en |
| dc.pending | false | |
| dc.publisher | University of Waterloo | en |
| dc.relation.uri | https://github.com/siqingh/llm_retrieve_supporting_evidence | en |
| dc.subject | information retrieval | en |
| dc.subject | natural language processing | en |
| dc.title | Retrieving Supporting Evidence for Generative Question Answering | en |
| dc.type | Master Thesis | en |
| uws-etd.degree | Master of Mathematics | en |
| uws-etd.degree.department | David R. Cheriton School of Computer Science | en |
| uws-etd.degree.discipline | Computer Science | en |
| uws-etd.degree.grantor | University of Waterloo | en |
| uws-etd.embargo.terms | 0 | en |
| uws.contributor.advisor | Clarke, Charles | |
| uws.contributor.affiliation1 | Faculty of Mathematics | en |
| uws.peerReviewStatus | Unreviewed | en |
| uws.published.city | Waterloo | en |
| uws.published.country | Canada | en |
| uws.published.province | Ontario | en |
| uws.scholarLevel | Graduate | en |
| uws.typeOfResource | Text | en |