Papers with writing tasks

9 papers
How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to detect AI-generated text are inadequate, causing misuse of the text.
Approach: They propose a universal evasive prompt framework that can prompt any PLM to generate “human-like” text that can mislead detectors.
Outcome: The proposed approach can prompt any PLM to generate “human-like” text that can mislead detectors.
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.
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text (2025.acl-long)

Copied to clipboard

Challenge: Qualitative analysis of experts’ free-form explanations shows that while they rely heavily on specific lexical clues (‘AI vocabulary’), they also pick up on more complex phenomena within the text (e.g., formality, originality, clarity).
Approach: They hire annotators to read 300 non-fiction English articles, label them as either human-written or AI-generated, and provide paragraph-length explanations for their decisions.
Outcome: The annotators who frequently use LLMs for writing tasks outperform commercial and open-source detectors even without evasion tactics like paraphrasing and humanization.
Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs (2025.coling-main)

Copied to clipboard

Challenge: a fine-tuned small language model (SLM) can generate human-like text, but it requires immense computational resources and large datasets.
Approach: They evaluate the creative writing abilities of a fine-tuned small language model, BART-large . they compare it to human writers and two large language models: GPT-3.5 and GPT-4o .
Outcome: The proposed model outperforms human writers and two large language models in two experiments . the results highlight how model size and fine-tuning influence creativity, fluency, and coherence .
LLMCrit: Teaching Large Language Models to Use Criteria (2024.findings-acl)

Copied to clipboard

Challenge: Current research on using criteria to provide feedback on tasks is limited . a general framework that can be used to teach large language models to use criteria is lacking .
Approach: They propose a framework that enables large language models to use criteria for feedback . criteria are extracted from guidelines and construct in-context demonstrations for each criterion .
Outcome: The proposed framework can be used to provide natural language feedback on tasks.
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)

Copied to clipboard

Challenge: a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Approach: They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Outcome: The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains.
Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Existing writing assistants rely on supervised fine-tuning to optimize models for multiple revisions.
Approach: They propose a framework that enhances WA performance with rationale and alignment.
Outcome: The proposed framework outperforms state-of-the-art WAs and the closed-source GPT-4o by 3.9 and 7.1 points on average across eight well-established writing-related test sets.
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)

Copied to clipboard

Challenge: Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF.
Approach: They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench.
Outcome: The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%.
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style (2026.acl-long)

Copied to clipboard

Challenge: Despite the growing use of large language models for writing tasks, it remains unclear whether users can effectively reshape LLM-generated text to reflect their personal style.
Approach: They conduct an online study in which participants post-edit LLM-generated drafts for writing tasks where personal style matters to them.
Outcome: The results show that post-editing increases stylistic similarity to unassisted writing and reduces similarity with fully LLM-generated output.

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