Papers with machine-generated text
Detecting Machine-Generated Text: Techniques and Challenges (2024.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial focuses on machine-generated text and deepfakes. |
| Approach: | This tutorial aims to provide a comprehensive overview of text detection techniques . it will focus on machine-generated text and deepfakes . |
| Outcome: | This tutorial focuses on machine-generated text and deepfakes. |
Style Over Substance: Evaluation Biases for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Ranking the relative performance of large language models based on Elo ratings is gaining popularity . however, the extent to which humans and LLMs are capable evaluators remains uncertain . |
| Approach: | They propose to evaluate machine-generated text across multiple dimensions using the Elo rating system . they propose to use crowd-sourced and expert annotators to rank models based on Elo ratings . |
| Outcome: | The proposed method improves the quality of LLM-based evaluations, but there is no improvement in crowd-sourced evaluations. |
Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors (2024.eacl-short)
Copied to clipboard
| Challenge: | Using large language models to detect machine generated text is difficult for humans to distinguish between human-written and machine-generated text. |
| Approach: | They propose to use one language model to detect machine-generated text produced by another language model in a zero-shot way. |
| Outcome: | The proposed methods can detect machine-generated text without additional training/data. |
M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection (2024.eacl-long)
Copied to clipboard
Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Toru Sasaki, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov
| Challenge: | Large language models generate fluent responses to user queries, but they are also susceptible to misuse in journalism, education, and academia. |
| Approach: | They propose a large-scale benchmark for machine-generated text detection that is a multi-generator, multi-domain, and multi-lingual corpus. |
| Outcome: | The proposed system can detect machine-generated text and pinpoint misuse . the proposed system is based on a large-scale benchmark dataset . |
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on this topic focus on the robustness of specific detectors or particular attack methods. |
| Approach: | They stress test the detectors’ robustness to malicious attacks under realistic scenarios using LLMs and metric-based detectors. |
| Outcome: | The proposed methods are based on a set of LLM-based models and their performance is compared under different budget levels. |
Automatic Detection of Generated Text is Easiest when Humans are Fooled (2020.acl-main)
Copied to clipboard
| Challenge: | Recent advances in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. |
| Approach: | They compare decoding methods with popular sampling-based decoding strategies . they show that multi-sentence excerpts can fool expert human raters over 30% of the time . |
| Outcome: | The proposed methods improve with longer excerpt length, but multi-sentence excerpts fool human raters over 30% of the time. |
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection (2024.acl-long)
Copied to clipboard
Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohammed Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov
| Challenge: | Large Language Models (LLMs) have brought an unprecedented surge in machine-generated text (MGT) societal implications are posed by their potential misuse and lack of training data. |
| Approach: | They propose a benchmark to detect machine-generated text in multiple languages . they use multi-domain and multi-generator corpus to identify which model generated the text . |
| Outcome: | The proposed benchmark compares a multilingual, multi-domain and multi-generator corpus of MGTs with human-generated content. |
Advancing Beyond Identification: Multi-bit Watermark for Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to detect machine-generated text focus on detection, but some misuses require tracing the adversary user for counteracting them. |
| Approach: | They propose a method for embedding traceable multi-bit information during language model generation. |
| Outcome: | The proposed method outperforms existing methods in terms of robustness and latency while maintaining text quality. |
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Toxic language detection systems often falsely flag text that contains minority group mentions as toxic . this over-reliance on spurious correlations also causes systems to struggle with detecting implicitly toxic language. |
| Approach: | They develop a machine-generated dataset of toxic and benign statements about 13 minority groups that generates subtly toxic and harmless text with a massive pretrained language model. |
| Outcome: | The proposed method can detect toxic and benign statements on a large scale . it can also detect hate speech on 94.5% of the toxic examples . |
Who Wrote this Code? Watermarking for Code Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect machine-generated text by embedding watermarks fail to function appropriately in code generation tasks due to the task’s nature of having low entropy. |
| Approach: | They propose a logit-modifying watermark method which enhances detection ability and mitigates code quality degeneration by removing low-entropy segments at generating and detecting watermarks. |
| Outcome: | The proposed method outperforms baseline methods in detecting machine-generated code text while preserving code quality. |
MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types (2023.findings-acl)
Copied to clipboard
Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury, Chulaka Gunasekara, Maxwell Crouse, Diwakar Mahajan, Ibrahim Abdelaziz, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Alexander Gray
| Challenge: | Existing evaluation metrics for machine text are inadequate to capture quality of text . a recent study has focused on task-specific evaluation metrics or on properties of machine-generated text based on mismatch errors . |
| Approach: | They propose a new evaluation scheme based on fine-grained mismatch errors . they propose 13 mismatch error types to guide the model for better prediction of human judgments . |
| Outcome: | The proposed evaluation scheme is based on mismatch errors in 7 NLP tasks . the mismatch error types guide the model for better prediction of human judgments . |
Ranking Human and LLM Texts Using Locality Statistics (2026.findings-eacl)
Copied to clipboard
| Challenge: | The paper extends the Data Movement Distance (DMD) metric defined to measure the locality in computer memory to text by defining a new term designed to better characterize low-frequency tokens. |
| Approach: | They propose to define a normalized version of the Data Movement Distance (nDMD) term is designed to better characterize low-frequency tokens. |
| Outcome: | The proposed normalized version outperforms baselines and improves performance on the English subset of the M4 dataset and the GenAI detection shared task. |
Exploring the Limitations of Detecting Machine-Generated Text (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in the quality of the generation of text by large language models have spurred research into identifying machine-generated text. |
| Approach: | They audit classification performance for detecting machine-generated text by evaluating on texts with varying writing styles. |
| Outcome: | The proposed methods are highly sensitive to stylistic changes and complexity, and in some cases degrade entirely to random classifiers. |
On the Zero-Shot Generalization of Machine-Generated Text Detectors (2023.findings-emnlp)
Copied to clipboard
| Challenge: | rampant proliferation of large language models generates text indistinguishable from human-written language. |
| Approach: | They train neural detectors on outputs of a new generator and test their performance on held-out generators. |
| Outcome: | The proposed detectors can be built on training data from medium-sized models. |
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation methods for natural language generation are inadequate . distinguishing machine-generated text is challenging even for human evaluators . |
| Approach: | They compare human-based evaluators with automated evaluation procedures . they find human evaluers do not correlate well with discriminative evalators . |
| Outcome: | The proposed evaluation methods are compared with a dozen state-of-the-art generators for online product reviews. |
WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses. |
| Approach: | They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks. |
| Outcome: | The proposed approach preserves the expressive power of large language models while preserving watermark detectability. |
Unmasking the Imposters: How Censorship and Domain Adaptation Affect the Detection of Machine-Generated Tweets (2025.coling-main)
Copied to clipboard
| Challenge: | generative AI has been used to generate fluent and convincing text on social media platforms . a new study examines the generative capabilities of four popular large language models . |
| Approach: | They propose a methodology to examine the generative capabilities of four prominent LLMs on Twitter using a dataset from Llama 3, Mistral, Qwen2 and GPT4o. |
| Outcome: | The proposed method examines the generative capabilities of four prominent LLMs on Twitter. |
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)
Copied to clipboard
Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu
| Challenge: | Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability. |
| Approach: | They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures. |
| Outcome: | The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios. |
RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors (2024.acl-long)
Copied to clipboard
Liam Dugan, Alyssa Hwang, Filip Trhlík, Andrew Zhu, Josh Magnus Ludan, Hainiu Xu, Daphne Ippolito, Chris Callison-Burch
| Challenge: | Existing methods for detecting machine-generated text are often insufficiently robust and lack benchmark datasets. |
| Approach: | They evaluate the out-of-domain and adversarial robustness of 8 open- and 4 closed-source detectors using RAID benchmark datasets. |
| Outcome: | The proposed detectors are fooled by adversarial attacks, repetition penalties, and unseen generative models. |
Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack (2024.lrec-main)
Copied to clipboard
| Challenge: | Despite the development of large language models, there are still significant challenges in detecting whether text is generated by a machine. |
| Approach: | They propose a framework for a broader class of adversarial attacks to perform minor perturbations in machine-generated content to evade detection. |
| Outcome: | The proposed framework can be compromised in as little as 10 seconds, and improves over iterative adversarial learning. |
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models generate huge amounts of text, making it impractical to manually distinguish whether a text is machine-generated. |
| Approach: | They propose two methods to detect machine-generated text by leveraging Log-Rank information and propose a faster method that uses less perturbations to achieve the same level of performance. |
| Outcome: | The proposed methods improve over the state of the art by 3.9 and 1.75 AUROC points absolute and require less perturbations to achieve the same level of performance. |
HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring (2025.acl-long)
Copied to clipboard
| Challenge: | Existing literature focuses on binary, document-level detection, neglecting texts composed jointly by human and LLM contributions. |
| Approach: | They propose to use a dataset to generate human-AI coauthored texts via an automatic pipeline with word-level attribution labels. |
| Outcome: | The proposed method can detect human-AI coauthored texts with a numeric AI ratio. |
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)
Copied to clipboard
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen
| Challenge: | Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation. |
| Approach: | They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts . |
| Outcome: | The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results. |
Authorship Attribution in Multilingual Machine-Generated Texts (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have reached human-like fluency and coherence, but distinguishing machine-generated text from human-written content becomes increasingly difficult. |
| Approach: | They propose a problem of multilingual authorship attribution (AA) that involves attributing texts to human or multiple LLM generators across diverse languages. |
| Outcome: | The proposed method can be adapted to multilingual settings, but still has significant limitations and challenges. |