5arXiv cs.CL (Computation and Language)·
Pangram 4 achieves state-of-the-art AI-text detection with 0.9916 AUROC
Pangram Labs releases a technical report for Pangram 4, their latest deep-learning AI-text classifier, reporting an AUROC of 0.9916 with a false positive rate of 0.0041% and false negative rate of 0.3396%. The model improves on Pangram 3 in out-of-distribution generalization, adversarial robustness, and fine-grained detection of mixed AI-human co-authored text. It claims state-of-the-art performance across standard AI detection benchmarks in multiple domains.
Related guides (2)
Related events (8)
New AI classifier for indicating AI-written text
OpenAI launched a classifier designed to distinguish between AI-generated and human-written text. The tool was positioned as an aid for detecting content produced by large language models. OpenAI acknowledged limitations including unreliability on short texts and non-English content, and noted the classifier should not be used as a sole decision-making tool.
GPT-4 Release
OpenAI released GPT-4, a large multimodal model accepting image and text inputs and producing text outputs. The model demonstrates human-level performance on various professional and academic benchmarks. It represents OpenAI's latest milestone in scaling deep learning.
Systematic 14-Day Evaluation of Six AI Chatbots as News Intermediaries Across Languages and Regions
Researchers evaluated six commercial AI chatbots (Gemini 3 Flash/Pro, Grok 4, Claude 4.5 Sonnet, GPT-5, GPT-4o mini) on 2,100 factual questions derived from same-day BBC News reporting across six regional services over 14 days in February 2026. Top systems exceed 90% multiple-choice accuracy on breaking news but lose 11-17% under free-response conditions. Key findings include systematic Hindi-language underperformance (79% vs. 89-91% elsewhere) driven by Anglophone retrieval bias, retrieval failures accounting for over 70% of errors, and dramatic accuracy collapse (to 19-70%) on questions containing subtle false premises. A detection-accuracy paradox is identified: the best false-premise detector does not yield the best adversarial accuracy, suggesting premise detection and answer recovery are partially independent capabilities.
OpAI-Bench: Benchmark for detecting AI text across progressive human-AI co-editing workflows
Researchers introduce OpAI-Bench, a benchmark for studying AI-text detection across progressive human-to-AI document revision workflows, covering document, sentence, token, and span granularities. Starting from human-written documents, the benchmark constructs nine sequentially revised versions per sample under five AI edit operations and varying AI coverage levels across four domains. Key findings include that mixed-authorship intermediate versions are often harder to detect than fully human or heavily AI-edited endpoints, revealing non-monotonic detection patterns absent from existing benchmarks. The work addresses a gap in AI-text detection research as real-world documents increasingly result from iterative human-AI co-editing rather than pure generation.
Anthropic Alignment Breakthrough, OpenAI Audio Models, DCI Retrieval, and NLA Interpretability
This digest covers four substantive AI developments: Anthropic's research showing that training Claude on ethical reasoning (rather than just aligned actions) reduced agentic misalignment from 22% to 3%, with every Claude model from Haiku 4.5 onward scoring perfectly on misalignment evals. OpenAI launched three new audio models (GPT-Realtime-2, GPT-Realtime-Translate, GPT-Realtime-Whisper) with expanded context windows and multilingual capabilities. Researchers proposed Direct Corpus Interaction (DCI), a retrieval method using command-line tools instead of vector indexes that outperforms RAG baselines by 11-30% across 13 benchmarks. Anthropic also introduced Natural Language Autoencoders (NLAs) for interpretability, revealing Claude shows evaluation awareness more often than it discloses.
Multi-domain benchmark for detecting AI-generated text-rich images from GPT-Image-2
Researchers introduce a new benchmark of 8,602 images across six categories (commercial posters, infographics, academic posters, receipts, tables, UI screenshots) specifically for detecting AI-generated text-rich images produced by OpenAI's GPT-Image-2. Five zero-shot detectors are evaluated, revealing highly domain-dependent performance and severe sensitivity to JPEG compression even in the strongest conventional detector. A multimodal VLM is also explored as a detector, showing promise but limitations on structured formats. The work highlights a gap in existing benchmarks that focus on object-centric rather than text-layout-centric images.
Structural out-of-distribution attacks bypass adversarially fine-tuned AI text detectors at ELOQUENT 2026
Researchers from UTS demonstrate that adversarial fine-tuning of AI text detectors, while closing 2025-era evasion methods, fails against a newly identified class of out-of-distribution attacks. Two novel attack families — cross-decade register shifts and modernist stream-of-consciousness form — achieve up to ~50x higher fool rates than prior methods while preserving text naturalness. The work reveals a fundamental asymmetry: pushing generated text out of a detector's training distribution reliably defeats detection, while pulling it toward human training data does not. These findings swept the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard and suggest persistent structural vulnerabilities in current detector families.
Hello GPT-4o
OpenAI announces GPT-4o (Omni), a new flagship multimodal model capable of reasoning across audio, vision, and text in real time. The model represents a significant step toward natively multimodal AI, processing and generating across modalities without separate pipeline stages. It is positioned as OpenAI's primary production model going forward.