Stacey, J;
Minervini, P;
Dubossarsky, H;
Camburu, OM;
Rei, M;
(2024)
Atomic Inference for NLI with Generated Facts as Atoms.
In:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
(pp. pp. 10188-10204).
Association for Computational Linguistics (ACL): Miami, FL, USA.
Preview |
Text
2024.emnlp-main.569.pdf - Published Version Download (1MB) | Preview |
Abstract
With recent advances, neural models can achieve human-level performance on various natural language tasks. However, there are no guarantees that any explanations from these models are faithful, i.e. that they reflect the inner workings of the model. Atomic inference overcomes this issue, providing interpretable and faithful model decisions. This approach involves making predictions for different components (or atoms) of an instance, before using interpretable and deterministic rules to derive the overall prediction based on the individual atom-level predictions. We investigate the effectiveness of using LLM-generated facts as atoms, decomposing Natural Language Inference premises into lists of facts. While directly using generated facts in atomic inference systems can result in worse performance, with 1) a multi-stage fact generation process, and 2) a training regime that incorporates the facts, our fact-based method outperforms other approaches.
| Type: | Proceedings paper |
|---|---|
| Title: | Atomic Inference for NLI with Generated Facts as Atoms |
| Event: | 2024 Conference on Empirical Methods in Natural Language Processing |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.18653/v1/2024.emnlp-main.569 |
| Publisher version: | https://doi.org/10.18653/v1/2024.emnlp-main.569 |
| Language: | English |
| Additional information: | © 2024 ACL. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10205678 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
