Papers arxiv:2605.27921 Show, Don't TELL: Explainable AI-Generated Text Detection Published on May 27 Submitted by Suraj Ranganath on Jun 2 Authors: , Suraj Ranganath Abstract A novel AI-generated text detection system named TELL is introduced that combines high-performance detection with native ex… …
Papers arxiv:2605.10977 PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks Published on May 9 Submitted by Sicheng Feng on May 13 HKUSTGZ Authors: Zhenxin Ai , Haiyun He Abstract PASA is a robust watermarking algorithm for large language… …
… It provides fine-grained textual annotations of visual observations across four forensic dimensions Texture, Lighting, Motion, Physics and verdict-consistent explanations synthesized via a multi-model aggregation and conflict-resolution pipeline. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Watermarking embeds statistical signatures in AI-generated text for detection and attribution. We reveal a fundamental vulnerability: when users access multiple models today's reality , watermarks trivially fail. …
Papers arxiv:2606.03348 SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation Published on Jun 2 Submitted by Junxiao Yang on Jun 3 Authors: , , , , , , Abstract AI-generated images with realistic text and layouts pose a significant misinformation threat requiring … …
Papers arxiv:2606.06113 Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback Published on Jun 4 Submitted by Huaisong Zhang on Jun 12 Kolors Team, Kuaishou Technology Authors: Huaisong Zhang , , Yuxuan Zhang , , , , , , , Abstract Structured Defect Grounding SDG … …
… Given an image and its paired text, the goal is to recover all correspondences between visually referential text spans and instance-level image segments, without assuming that the relevant text spans are provided. …
… The following papers were recommended by the Semantic Scholar API Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image Detection 2026 Domain Generalization via Text-Anchored Information Bottleneck 2026 Learning to Compose: Revisiting Proxy Task Design for Zero-Sho… …
… Importantly, our method is \textit{training-agnostic}: it works for both parameter-efficient fine-tuning methods like LoRA and full-parameter tuning, as the gradient analysis operates independently of which parameters are being updated during training. …
… Some posts may also reframe actual events within a manipulative context. To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. …