Papers by Nafis Irtiza Tripto

5 papers
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.
Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors (2025.findings-emnlp)

Copied to clipboard

Challenge: Personal style is often subtle and implicit, making it difficult to specify through prompts yet essential for user-aligned generation.
Approach: They evaluate LLMs' ability to imitate personal writing styles via in-context learning from user-authored samples.
Outcome: The proposed model can imitate personal writing styles from a small number of user-authored samples.
CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysis (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies on LLM-LLM collaboration for open-ended tasks have focused on human-LLm interaction.
Approach: They propose to generate a dataset exclusively for LLMs to explore multi-LLM collaboration scenarios . they extend their authorship-related tasks for multi-llm settings and extend their baselines .
Outcome: The authors extend authorship-related tasks for multi-LLM settings and present baselines for LLM-LLMS collaboration.
A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts (2024.acl-long)

Copied to clipboard

Challenge: Using a computational approach, we discover that diminishing performance in text classification models is closely associated with the extent of deviation from the original author’s style.
Approach: They propose to use large language models to determine whether a text retains original authorship when it undergoes numerous paraphrasing iterations.
Outcome: The results suggest that authorship should be task-dependent .
Authorship Obfuscation in Multilingual Machine-Generated Text Detection (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Language Modeling have birthed Large Language Models (LLMs), which exhibit significant improvements, including the ability to generate texts easily misconstrued as humanwritten.
Approach: They compare authorship obfuscation methods against machine-generated text (MGT) in 11 languages and analyze their performance against 37 well-known AO methods.
Outcome: The proposed methods can cause evasion of detection in all languages, with homoglyph attacks particularly successful.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations