llm-detection

Tag

Cards List
#llm-detection

MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts

arXiv cs.CL · 2026-09-03 Cached

MultiGhostBench is a multilingual benchmark for long-form LLM-generated text attribution under distribution shifts, featuring 928 books in six languages and highlighting performance degrades and no single method consistently best across settings.

0 favorites 0 likes
#llm-detection

Robot comment classifier

Lobsters Hottest · 2026-08-22 Cached

The article describes a tool that distinguishes AI-generated comments from human-written ones in code using linguistic features like character frequency, and discusses its methodology and implications.

0 favorites 0 likes
#llm-detection

Most biomedical publications show signs of LLM-assisted writing

arXiv cs.CL · 2026-08-12 Cached

A preprint estimates that by the end of 2025, 89% of open-access biomedical papers show signs of LLM-assisted writing, using a new word-frequency-based method.

0 favorites 0 likes
#llm-detection

EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection

arXiv cs.CL · 2026-08-12 Cached

This paper presents EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for detecting LLM-generated, refined, and human-written Chinese text in the NLPCC 2026 Shared Task 6, achieving first place with a macro-F1 of 0.8888.

0 favorites 0 likes
#llm-detection

MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection

arXiv cs.CL · 2026-08-12 Cached

MD-ProTector is a research paper proposing a prototype-based method for LLM-generated text detection, using multiple trainable reference vectors per class to capture within-class variation and improve robustness across domains, generators, languages, and adversarial edits.

0 favorites 0 likes
#llm-detection

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration

arXiv cs.CL · 2026-08-07 Cached

This paper proposes EchoPrompt, a training-free detector for LLM-generated text that restores a latent prompt dependency by prepending a generic prefix and measuring likelihood gain differences between instruction-tuned and base models, achieving state-of-the-art zero-shot detection performance.

0 favorites 0 likes
#llm-detection

I flagged two research papers for fake authors and both were accepted as orals

Hacker News Top · 2026-07-30 Cached

A reviewer recounts flagging two papers with fabricated authors that were accepted as orals, and reports that 68% of 22 reviewed submissions contained fabricated citations, LLM-generated content, or fake author lists. Multiple studies confirm tens of thousands of such papers in 2025 alone, with peer reviews increasingly AI-generated.

0 favorites 0 likes
#llm-detection

Introducing Pangram 4 (2 minute read)

TLDR AI · 2026-07-30 Cached

Pangram Labs announces Pangram 4, its most powerful AI detector yet, with significantly reduced false positive and false negative rates, robust detection across frontier models, and new image scan features.

0 favorites 0 likes
#llm-detection

DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection

arXiv cs.CL · 2026-07-27 Cached

Introduces DWT-Fusion, a training-free framework using discrete wavelet analysis of token log-probabilities for detecting LLM-generated text, achieving strong AUROC results on multiple datasets.

0 favorites 0 likes
#llm-detection

Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content

arXiv cs.CL · 2026-07-24 Cached

This paper investigates how well LLMs can detect their own generated content in educational contexts, finding that detection accuracy varies by task type and is unreliable for short-answer questions.

0 favorites 0 likes
#llm-detection

Detecting LLM-Generated Texts with "Classical" Machine Learning

Hacker News Top · 2026-07-16 Cached

A developer explores using classical machine learning to detect LLM-generated web fiction, creating an open-source demo and model with ~85% single-sentence accuracy.

0 favorites 0 likes
#llm-detection

Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability

arXiv cs.CL · 2026-07-07 Cached

The paper introduces Telescope Perplexity, a metric that measures token repetition probability to detect LLM-generated text in a zero-shot manner, achieving state-of-the-art or competitive performance across diverse datasets.

0 favorites 0 likes
#llm-detection

@ChinmayKak: New blog! This blog is about whether we can RL a small model to catch LLMs in writing, and have a sense of which model …

X AI KOLs Timeline · 2026-06-28 Cached

This blog post explores using reinforcement learning to train a small model to detect writing styles of different LLMs, providing code and traces.

0 favorites 0 likes
#llm-detection

@panickssery: In addition to identifying LLM use, Pangram has identified many academics who don't know the difference between false p…

X AI KOLs Following · 2026-06-22

Pangram, a tool for detecting LLM use, reveals that many academics do not understand the difference between false positives and false negatives.

0 favorites 0 likes
#llm-detection

Detecting undisclosed LLM-generated content in parliamentary texts

arXiv cs.CL · 2026-06-15 Cached

This paper evaluates the extent of undisclosed LLM-generated content in parliamentary texts from the UK and Sweden by training an interpretable text classifier, finding a steady increase in undisclosed LLM use from 2022 onwards.

0 favorites 0 likes
#llm-detection

Human proof for FOSS contributions

Lobsters Hottest · 2026-05-25 Cached

Rodrigo Arias Mallo proposes using asciinema recordings as proof of human authorship for FOSS contributions to Dillo, arguing that LLMs struggle to convincingly generate such recordings.

0 favorites 0 likes
#llm-detection

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection

arXiv cs.CL · 2026-05-18 Cached

DetectRL-X is a comprehensive multilingual benchmark for evaluating LLM-generated text detectors across 8 languages and 6 domains, including stress testing with AI-assisted writing operations and perturbations. It reveals strengths and limitations of current detectors in multilingual scenarios.

0 favorites 0 likes
#llm-detection

Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text

arXiv cs.CL · 2026-05-08 Cached

This paper addresses the degradation of likelihood-based machine-generated text detectors by identifying a Simpson's paradox in token-score aggregation. It proposes a learned local calibration step that significantly improves detection performance across various models and datasets.

0 favorites 0 likes
#llm-detection

Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation

arXiv cs.CL · 2026-05-08 Cached

Proposes LiSCP, a lightweight stylistic consistency profiling method for robust detection of LLM-generated textual content, focusing on feature stability under adversarial manipulation. Achieves superior performance on in-domain and cross-domain detection with notable robustness.

0 favorites 0 likes
#llm-detection

Quoting Andrew Kelley

Simon Willison's Blog · 2026-04-30 Cached

Andrew Kelley, creator of Zig, argues that LLM-assisted contributions are detectable through distinct mistakes and a 'digital smell,' comparing it to smoking in a non-smoking house.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback