Papers with detection method
Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are ubiquitous and capable of generating long coherent texts that look almost indistinguishable from human-written texts. |
| Approach: | They propose to use watermark and automatic detection to detect synthetic texts generated from Large Language Models (LLMs) they evaluate six different models, six different watermark techniques and two different automatic detectors for different levels of syntactic changes. |
| Outcome: | The proposed methods outperform on unperturbed and perturbed datasets on six different sizes of Qwen2.5 models, six watermark techniques and detectors, and two automatic detectors. |
Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation (2022.naacl-main)
Copied to clipboard
| Challenge: | Detecting out-of-context media is a problem in domains of public significance . a method that leverages automatically generated hard image-text mismatches is proposed . |
| Approach: | They propose a method that leverages automatically generated hard image-text mismatches to detect out-of-context media . they analyze tweets relevant to topics such as COVID-19, Climate Change and Military Vehicles . |
| Outcome: | The proposed method improves detection accuracy over a strong baseline on a set of fakes created by humans. |
RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks (2023.acl-long)
Copied to clipboard
| Challenge: | Existing defenses focus on improving robustness of the victim model in training, but neglect to mitigate adversarial attacks during inference. |
| Approach: | They propose a framework that confuses attackers and corrects adversarial contexts . their framework helps improve the robustness of the victim model during inference . |
| Outcome: | The proposed framework improves the robustness of the victim model in training . it also corrects abnormal contexts in the representation level and filtering out examples . |
Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models (2024.acl-long)
Copied to clipboard
Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen
| Challenge: | Despite the impressive multilingual capabilities demonstrated by LLMs, the understanding of how these abilities develop and function remains nascent. |
| Approach: | They propose a novel detection method to pinpoint language-specific neurons within LLMs by selectively activating or deactivating these neurons. |
| Outcome: | The proposed method can “steer” the output language of LLMs by selectively activating or deactivating language-specific neurons. |
PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent methods for detecting LLM-generated text have shown impressive performance, but in real-world scenarios, users often introduce perturbations to the text. |
| Approach: | They propose a method that detects syntactic trees that are minimally affected by perturbations and exhibit distinct differences between human-written and LLM-generated text. |
| Outcome: | The proposed method shows that it is significantly better against perturbations on the HC3 and GPT-3.5-mixed datasets and also has the shortest time expenditure. |
Enhancing LLM Text Detection with Retrieved Contexts and Logits Distribution Consistency (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting large language models (LLMs) generate fluent text, but they only use a few tokens due to the short length or insufficient information in some texts. |
| Approach: | They propose a method that leverages external text corpora to evaluate the difference in logit distribution of input text under retrieved human-written and LLM-rewritten contexts. |
| Outcome: | The proposed method achieves state-of-the-art performance in AUROC on five public datasets with three widely-used source LLMs. |
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | a growing number of researchers are studying the hallucination issue in large language models. |
| Approach: | They propose a hallucination detection benchmark and a method to detect hallucines in LLMs. |
| Outcome: | The proposed method detects hallucinations and mitigates them using different training stages. |
DRES: Fake news detection by dynamic representation and ensemble selection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for text-based fake news detection are limited due to context sensitivity and generalization issues. |
| Approach: | They propose a method that leverages instance hardness measures to estimate the classification difficulty for each news article across multiple textual feature representations. |
| Outcome: | The proposed method significantly improves over state-of-the-art methods, confirming the effectiveness of representation selection based on instance hardness and dynamic ensemble selection. |
KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Detecting LLM-generated text is crucial for academic integrity, preventing plagiarism, protecting copyrights, ethical research practices. |
| Approach: | They propose a method specifically designed for Korean language to detect LLM-generated text . they examine spacing patterns, part-of-speech diversity, and comma usage . |
| Outcome: | The proposed method achieves an average of 19.78% higher AUC-ROC compared to the best-performing detection method. |
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models (2025.acl-long)
Copied to clipboard
| Challenge: | Sticky tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance. |
| Approach: | They propose a method to detect “sticky tokens” by sentence and token filtering and apply it to 40 checkpoints across 14 model families. |
| Outcome: | The proposed method detects 868 sticky tokens across 14 models and shows that their presence does not correlate with model size or vocabulary size. |