LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History

Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark Gales, Mario Fritz


Abstract
With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successfully perform a wide range of tasks as part of a conversation. To provide some sort of memory and context, such approaches typically condition their output on the entire conversational history. Although this sensitivity to the conversational history can often lead to improved performance on subsequent tasks, we find that performance can in fact also be negatively impacted, if there is a _task-switch_. To the best of our knowledge, our work makes the first attempt to formalize the study of such vulnerabilities and interference of tasks in conversational LLMs caused by task-switches in the conversational history. Our experiments across 5 datasets with 15 task switches using popular LLMs reveal that many of the task-switches can lead to significant performance degradation.
Anthology ID:
2024.emnlp-main.811
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14633–14652
Language:
URL:
https://aclanthology.org/2024.emnlp-main.811
DOI:
10.18653/v1/2024.emnlp-main.811
Bibkey:
Cite (ACL):
Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark Gales, and Mario Fritz. 2024. LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14633–14652, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History (Gupta et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.811.pdf
Software:
 2024.emnlp-main.811.software.zip