Natural Language Processing

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 introduced a multi-factor scoring system to evaluate large language model responses, assessing accuracy, conciseness, factual consistency, readability, and coherence. Tests on the TruthfulQA dataset showed LL…

Researchers propose a programmatic solution for generating product advertising headlines using reinforcement learning on transformer-based masked language models. The method conditions on multiple products and outperform…

Researchers extended PubHealthBench, a public health QA benchmark, into a retrieval-augmented setting and found that hybrid retrieval consistently improves recall and ranking quality. Providing retrieved context substant…

Researchers propose a multimodal solution for audio sentiment analysis that integrates audio and automatically generated multilingual text transcripts via cross-modal transformers. The approach improves sentiment classif…

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,…

Telnyx launched two new managed insights, Agent Instruction Following and User Satisfaction, for AI Assistants to measure assistant quality without custom setup. The insights can be enabled via Insight Groups and queried…

Large language models produce fluent but unreliable translations that hide errors such as changed numbers, inconsistent terminology, and fractured names, because they are optimized for plausibility rather than accuracy a…

Researchers introduced Self-Reflective Program Search for Long Context (SRLM), a framework that uses uncertainty-aware self-reflection to improve long-context handling in language models. SRLM leverages self-consistency,…

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 …

Tesla is developing voice-intent support for its Full Self-Driving system, allowing drivers to give contextual instructions such as identifying the correct driveway or house near a destination, as confirmed by VP of AI S…