Tag
This paper introduces the one-sided conversation problem (1SC), addressing how to reconstruct missing dialogue and generate summaries when only one speaker's turns are available in real-world settings like telemedicine and call centers. The authors evaluate prompting and finetuned models on multiple datasets, finding that access to future context and utterance length information improves reconstruction, while high-quality summaries can be generated without full dialogue reconstruction.
This paper analyzes spontaneous dyadic Zoom conversations using multimodal features (acoustic, facial, turn-taking) to identify markers of perceived conversational success, finding that entrainment in speech and facial movements correlates with higher interaction quality.
This paper proposes multi-strategy utterance generation methods for Emotional Support Conversations (ESC), where each utterance can contain multiple strategy-response pairs. Two generation approaches (All-in-One and One-by-One) enhanced with cognitive reasoning via reinforcement learning are evaluated on the ESConv dataset, demonstrating improved supportive quality and dialogue success.
ClankerPass is a product that challenges users to convince an AI that they themselves are an AI, a reverse Turing test-style interaction.
Tines launches Story Copilot, a chat-based interface for building intelligent security workflows without code.
An introductory guide to using ChatGPT, covering basic prompting techniques, practical use cases, and voice/dictation features to help new users get started with the conversational AI assistant.
ServiceNow introduces EVA, a new end-to-end evaluation framework for conversational voice agents that jointly scores task accuracy and conversational experience.
OpenAI releases GPT-5.3 Instant, an update to ChatGPT's most-used model that improves conversational flow, reduces unnecessary refusals, and decreases hallucinations by up to 26.8% in high-stakes domains. The update focuses on tone, relevance, and practical usability based on user feedback.
Sneo.ai lets users chat with their SEO data to extract insights conversationally.
TRUSTBANK has integrated AI agents powered by OpenAI's API into its Furusato Choice platform to help users personalize hometown tax donation gifts through conversational recommendations and intelligent search.
Praktika is an AI-powered language learning app that uses a multi-agent system with GPT-5.2 and GPT-5 Pro to provide personalized conversational lessons that mimic real human tutors through adaptive lesson delivery, progress tracking, and dynamic learning planning.
Tolan, a voice-first AI companion built by Portola, uses GPT-5.1 and advanced memory management to create personalized, evolving conversations with animated characters. The platform leverages OpenAI's models, the Responses API, and vector databases to achieve near-instant latency and coherent long-form dialogue.
Scout24, Germany's largest real-estate platform, launched HeyImmo, a GPT-5 powered conversational search assistant that goes beyond traditional search to provide expert guidance through the home-buying process with adaptive answer formats and intelligent interaction.
India-based fintech CRED partnered with OpenAI to build AI-powered tools—Cleo (customer-facing chatbot), Thea (agent support), and Stark (operations SOP management)—resulting in a 14-point CSAT improvement and 98% resolution accuracy. The company is expanding these AI capabilities across all business lines to deliver concierge-like experiences at scale.
Lowe's has deployed GPT-4o-powered AI tools—Mylow for customers on Lowes.com and Mylow Companion for in-store associates—to provide expert home improvement guidance at scale. The partnership with OpenAI aims to transform Lowe's from a product-focused retailer to a project-expertise platform.
EliseAI, founded by Minna Song, uses conversational AI to improve efficiency in housing and healthcare industries. The company evolved from early NLP models like BERT to leveraging GPT-4 and voice AI technologies like Whisper to solve industry-specific challenges.
Typeform launches Formless, an AI-powered platform built on OpenAI's GPT-3.5 Turbo and GPT-4 that replaces traditional forms with dynamic conversational interactions. The platform enables natural, two-way dialogue for data collection where respondents can ask follow-up questions like in human conversation.
OpenAI is introducing custom instructions for ChatGPT, allowing users to set persistent preferences and requirements that the model will consider across all conversations. The feature launches in beta for Plus plan users and will expand to all users in coming weeks.
OpenAI introduces ChatGPT, a conversational AI model fine-tuned from GPT-3.5 using reinforcement learning from human feedback (RLHF). The model is designed to answer follow-up questions, admit mistakes, and reject inappropriate requests, with free access provided during the research preview.
Google I/O '26 keynote demonstrated AI acceleration across the board: 32 quadrillion tokens processed per month, over 900 million monthly active users for Gemini, new-generation TPU chips and world model Gemini Omni unveiled, along with conversational AI features such as Ask YouTube and Docs Live.