Natural Language Processing

Researchers propose R^3, a framework for rectifying textual violations in video advertisements while preserving original semantic intent. The system uses a group-relative compliance experience extractor and curriculum re…

Researchers propose an evaluation framework combining regularized regression on item text embeddings with repeated cross-validated R-squared and two performance upper bounds—a reliability ceiling and a design ceiling—to …

Researchers developed a benchmark to evaluate vision-language models' ability to use spatial deictic expressions across four languages. Tests showed that current models use demonstratives like "this" and "that" different…

Researchers studying harmful online communication in Discord cybercrime communities found that interpretation difficulty stems from slang, coded terms, and community-specific expressions. Their experiments showed that lo…

Researchers evaluated the relevance of several RAG metrics by comparing scores from four libraries (Ragas, DeepEval, RAGChecker, Opik) against human evaluators and standard metrics using a question-answering dataset. The…

Researchers developed SAMPA, a Whisper-based segmenter that transcribes Brazilian Portuguese speech while inserting markers for terminal prosodic boundaries. Fine-tuned on the NURC-SP dataset, SAMPA achieved competitive …

Researchers introduced SynthAVE, a large-scale benchmark for synthetic labeling of e-commerce attribute extraction, covering 12,726 products across 229 product types, 792 attributes, and four languages. They validated th…

A study on text-to-SQL systems found that verification-based signals, such as LLM judges, outperform black-box signals like self-consistency in predicting query correctness, with a two-provider ensemble achieving 0.82 AU…

Researchers found substantial cross-lingual disparities in healthcare LLM Q&A, with models aligning more with English Wikipedia even for non-English prompts. Providing non-English contextual excerpts improved factual ali…

A new 'humanizer' tool released on 20 June by Jie Ding, a machine-learning researcher at the University of Minnesota, can erase signs of AI-written text in papers and grant proposals. While some researchers praise it for…

A developer discovered that generic ChatGPT answers often stem from insufficient context in user prompts, not model limitations. By explicitly restating subjects, constraints, and desired formats in follow-up questions, …

Paperlist.ai introduces a tool that solves the 'context collapse' problem in academic reading by breaking research papers into structured, navigable summaries. This allows researchers to scan 10-15 papers on a topic effi…

A developer built a forensic media analyzer that scores articles on rhetorical structure rather than political bias, drawing on rhetoric, framing theory, and propaganda detection. The tool, exemplified by Rhetoric Audit,…

Roxana del Toro recounts the First (and Last) Intent-Inference Conference, reflecting on the challenges of distinguishing real from generated content in AI. The conference explored algorithms and tooling for intent infer…

Amotions launched an AI Zoom app that provides real-time guidance during sales calls, helping users ask better questions, handle objections, and stay aligned with their sales playbook. The app is visible only to the user…

OpenAI introduced GPT-Live, a new voice mode in the ChatGPT iPhone app that delegates complex tasks to GPT-5.5 while maintaining conversation flow. The model replaces an older GPT-4o era voice mode and includes improveme…

Meta is testing prototype 'super sensing' smart glasses that could continuously record audio and capture photos every few seconds, with metadata extracted and uploaded for AI queries rather than storing raw footage, acco…

In 1973, psychiatrist Kenneth Colby created PARRY, an ELIZA-style chatbot simulating a paranoid schizophrenic, and connected it to ELIZA (DOCTOR). Vint Cerf published the transcript as an RFC, showcasing an early chatbot…

OpenAI launched GPT-Live, a new voice model for ChatGPT that uses full-duplex architecture to enable continuous, natural dialogue with conversational fillers like 'mhmm'. The system processes speech and generates respons…

DocuBrowse, a new desktop application, turns local document collections into searchable knowledge bases using AI-powered semantic search and summaries, all running offline with no internet or API keys required. The tool …