paper-with-me

홈 › Papers

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

2024-02-28 · Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark Gales, Mario Fritz

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.

📄 PDF Abstract BibTeX arXiv:2402.18216

Code (1)

ivaxi0s/llm-task-switch 공식 구현

Similar Papers 제목 키워드 기반

When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry

2026-04-30 · Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti, Sebastian Risi arxiv

To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how repr…

Continual Learning

How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives

2023-05-24 · Xinpeng Wang, Leonie Weissweiler, Hinrich Schütze, Barbara Plank

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task…

Knowledge DistillationQNLI

Disentangling Task Interference within Neurons: Model Merging in Alignment with Neuronal Mechanisms

2025-03-07 · Zitao Fang, Guodong Du, Shuyang Yu, Yifei Guo 외

Fine-tuning pre-trained models on targeted datasets enhances task-specific performance but often comes at the expense of generalization. Model merging techniques, which integrate multiple fine-tuned models into a single …

Task Arithmetic

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity

2021-07-09 · Sebastian Lee, Sebastian Goldt, Andrew Saxe

Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new ta…

Continual Learning

Optimizing Placement and Power Allocation in Reconfigurable Intelligent Sensing Surfaces for Enhanced Sensing and Communication Performance

2024-09-10 · Cheng Luo, Jie Hu, Luping Xiang, Kun Yang 외

In this letter, we investigate the design of multiple reconfigurable intelligent sensing surfaces (RISSs) that enhance both communication and sensing tasks. An RISS incorporates additional active elements tailored to imp…