# Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits

arXiv: https://arxiv.org/abs/2409.14509 · HTML: https://mlsanity.com/paper/2409.14509/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 118 references that are in the map.
- First posted on arXiv 22 Sep 2024.

## Builds on (most cited first, 30 of 53)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Algorithmic Monoculture and Social Welfare](https://mlsanity.com/paper/2101.05853/) (2021)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Delving into LLM-assisted writing in biomedical publications through excess vocabulary](https://mlsanity.com/paper/2406.07016/) (2024)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers](https://mlsanity.com/paper/2211.05030/) (2022)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers](https://mlsanity.com/paper/2101.09157/) (2021)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models](https://mlsanity.com/paper/2402.11723/) (2024)

## Built on by (most cited first, 30 of 49)

- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [Idiosyncrasies in Large Language Models](https://mlsanity.com/paper/2502.12150/) (2025)
- [Beemo: Benchmark of Expert-edited Machine-generated Outputs](https://mlsanity.com/paper/2411.04032/) (2024)
- [EditLens: Quantifying the Extent of AI Editing in Text](https://mlsanity.com/paper/2510.03154/) (2025)
- [AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation](https://mlsanity.com/paper/2504.07532/) (2025)
- [Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models](https://mlsanity.com/paper/2506.05339/) (2025)
- [EvalAgent: Discovering Implicit Evaluation Criteria from the Web](https://mlsanity.com/paper/2504.15219/) (2025)
- [Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models](https://mlsanity.com/paper/2505.16245/) (2025)
- [Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books](https://mlsanity.com/paper/2601.18353/) (2026)
- [StoryScope: Investigating idiosyncrasies in AI fiction](https://mlsanity.com/paper/2604.03136/) (2026)
- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [Writing as a testbed for open ended agents](https://mlsanity.com/paper/2503.19711/) (2025)
- [Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers](https://mlsanity.com/paper/2510.13939/) (2025)
- [Optimizing Diversity and Quality through Base-Aligned Model Collaboration](https://mlsanity.com/paper/2511.05650/) (2025)
- [Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays](https://mlsanity.com/paper/2503.20062/) (2025)
- [FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning](https://mlsanity.com/paper/2505.14271/) (2025)
- [A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users](https://mlsanity.com/paper/2509.18632/) (2025)
- [Measuring AI "Slop" in Text](https://mlsanity.com/paper/2509.19163/) (2025)
- [Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity](https://mlsanity.com/paper/2509.22641/) (2025)
- [Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains](https://mlsanity.com/paper/2510.17793/) (2025)
- [Phraselette: A Poet's Procedural Palette](https://mlsanity.com/paper/2503.06335/) (2025)
- [LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers](https://mlsanity.com/paper/2602.16162/) (2026)
- [DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition](https://mlsanity.com/paper/2507.18802/) (2025)
- [CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection](https://mlsanity.com/paper/2509.04460/) (2025)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [MuseScorer: Idea Originality Scoring At Scale](https://mlsanity.com/paper/2505.16232/) (2025)
- [Guiding Generative Storytelling with Knowledge Graphs](https://mlsanity.com/paper/2505.24803/) (2025)
- [Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling](https://mlsanity.com/paper/2601.07149/) (2026)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- [RevTogether: Supporting Science Story Revision with Multiple AI Agents](https://mlsanity.com/paper/2503.01608/) (2025)

## Abstract (arXiv)

LLM-based applications are helping people write, and LLM-generated text is making its way into social media, journalism, and our classrooms. However, the differences between LLM-generated and human written text remain unclear. To explore this, we hired professional writers to edit paragraphs in several creative domains. We first found these writers agree on undesirable idiosyncrasies in LLM generated text, formalizing it into a seven-category taxonomy (e.g. clich'es, unnecessary exposition). Second, we curated the LAMP corpus: 1,057 LLM-generated paragraphs edited by professional writers according to our taxonomy. Analysis of LAMP reveals that none of the LLMs used in our study (GPT4o, Claude-3.5-Sonnet, Llama-3.1-70b) outperform each other in terms of writing quality, revealing common limitations across model families. Third, building on existing work in automatic editing we evaluated methods to improve LLM-generated text. A large-scale preference annotation confirms that although experts largely prefer text edited by other experts, automatic editing methods show promise in improving alignment between LLM-generated and human-written text.