Skip to content

Toggle service links

Large Language Models for Scientific Question Answering: an Extensive Analysis of the SciQA Benchmark
Mr Antonello Meloni

This event will take place on 23rd July 2024 at 11:30am (10:30 GMT)
Knowledge Media Institute, Berrill Building, The Open University, Milton Keynes, United Kingdom, MK7 6AA

The SciQA benchmark for scientific question answering presents a challenging task for next-generation question-answering systems, where standard large language models often fall short. In this seminar, we will analyze the performance of language models on this benchmark, exploring both prompting and fine-tuning techniques to enhance their adaptability to the SciQA task. Our findings demonstrate that intelligent few-shot selection in prompting and targeted fine-tuning can lead to excellent results on the SciQA benchmark. We will also discuss valuable insights gained, common error categories encountered, and their implications for optimizing large language models for question answering over knowledge graphs.

The webcast is open to 300 users

download calendar file (e.g. for MS Outlook and iCal)

This page will automatically refresh every 3 minutes on javascript enabled browsers. Buttons to enter the webcast will appear below 5 minutes prior to the start of the event.
Creative Commons Licence KMi logo