SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.08152 · EMNLP · 2025

DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations

Cheng Chen, Tahmid Laskar, Xue-Yong Fu, Shashi Bhushan, Elena Khasanova, Harsh Saini

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The rapid advancements in Large Language Models (LLMs) have enabled their adoption in real-world industrial scenarios for various natural language processing tasks. However, the high inference cost of large-scale LLMs makes their deployment impractical, necessitating the use of smaller models. Despite their efficiency, smaller LLMs lack robust zeroshot instruction-following capabilities across diverse domains, limiting their adaptability to dynamic user requirements. Traditional finetuning approaches exacerbate this issue by inducing catastrophic forgetting, reducing the model's generalization ability for unseen tasks. In this paper, we propose Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension (DACIP-RC), a continual pre-training technique that enhances smaller LLMs' domain adaptability for business conversational tasks. Unlike conventional pre-training approaches that rely on next-token prediction, DACIP-RC generates diverse task instructions and responses via reading comprehension on conversation transcripts, enabling better instruction generalization. Our empirical evaluations demonstrate that DACIP-RC significantly improves zero-shot generalization across a wide range of business conversational tasks, including meeting summarization, action item generation, and call purpose identification. To the best of our knowledge, this is the first work to apply instruction pre-training on business conversational data, providing insights into how industries can leverage proprietary datasets for domain adaptation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2510.08152")
get_code_for_paper("2510.08152")
have("2510.08152")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2510.08152.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2510.08152.svg)](https://syntology.ai/paper/2510.08152)

Connect an agent — have() is free.