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

Anonymous

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 \emph{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.

Paper Type: short

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability

Languages Studied: English

Preprint Status: We are considering releasing a non-anonymous preprint in the next two months (i.e., during the reviewing process).

A1: yes

A1 Elaboration For Yes Or No: Section 6

A2: yes

A2 Elaboration For Yes Or No: Section 7

A3: yes

A3 Elaboration For Yes Or No: Abstract and Section 1

B: yes

B1: yes

B1 Elaboration For Yes Or No: Section 4.1 Experimental Setup

B2: yes

B2 Elaboration For Yes Or No: Section 7

B3: yes

B3 Elaboration For Yes Or No: Experimental setup 4.1 and Appendix A

B4: n/a

B5: n/a

B6: yes

B6 Elaboration For Yes Or No: Appendix A

C: yes

C1: yes

C1 Elaboration For Yes Or No: Section 4.1 Experimental Setup and Section 7

C2: yes

C2 Elaboration For Yes Or No: Section 4.1 Experimental Setup

C3: yes

C3 Elaboration For Yes Or No: We report single run since our experiments are extremely computationally heavy.

C4: yes

C4 Elaboration For Yes Or No: Appendix A

D: no

D1: n/a

D2: n/a

D3: n/a

D4: n/a

D5: n/a

E: no

E1: n/a