Papers by Mahjabin Nahar
Beyond Checkmate: Exploring the Creative Choke Points for AI Generated Texts (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on detecting LLM-generated text (AI text) has raised concerns about potential misuse . a new study examines the nuanced distinctions between human and AI texts . |
| Approach: | They analyze human-AI text differences across body, intro, conclusion segments . human texts exhibit greater stylistic variation across segments, they show . |
| Outcome: | The findings will inform their viability and boundaries as effective creative assistants to humans. |
Chain-of-Interactions: Multi-step Iterative ICL Framework for Abstractive Task-Oriented Dialogue Summarization of Conversational AI Interactions (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have introduced paradigm-shifting approaches in natural language processing, yet their transformative in-context learning (ICL) capabilities remain underutilized, especially in customer service dialogue summarization. |
| Approach: | They propose a single-instance, multi-step framework that orchestrates information extraction, self-correction, and evaluation through sequential interactive generation chains. |
| Outcome: | The proposed framework outperforms existing models and prompts in the customer service dialogue summarization domain. |