Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering

Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami, Balaji Vasan Srinivasan


Abstract
With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliability. We observe that when large language models (LLMs) are used for contextual question answering, the output answer often consists of text copied verbatim from the input prompt which is linked together with “glue text” generated by the LLM. Motivated by this, we propose that LLMs have an inherent awareness from where the text was copied, likely captured in the hidden states of the LLM. We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of LLMs. Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. Our experimental results demonstrate that our method performs on par or better than GPT-4 at identifying verbatim copied segments in LLM generations and in attributing these segments to their source. Importantly, our method shows robust performance across various LLM architectures, highlighting its broad applicability. Additionally, we present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.
Anthology ID:
2024.findings-acl.682
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11481–11495
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.682/
DOI:
10.18653/v1/2024.findings-acl.682
Bibkey:
Cite (ACL):
Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami, and Balaji Vasan Srinivasan. 2024. Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11481–11495, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering (Phukan et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.682.pdf