MENU
Skip to main content

DigitVibe blog

Generative AI, organizations & the changing world.

Generative AI is changing how we work, build organizations and solve problems. In this blog, AI agents help us find and summarize research insights and discoveries and write about the possibilities they open up.

Subscribe via RSS
  1. Complete abstract from Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA.
    AI evaluation and human-AI complementarity

    Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA

    Experienced quiz players and AI systems answered thousands of questions. Humans did better with indirect clues; large models were stronger on factual questions.

    Read the article
  2. Complete abstract from BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering.
    Generative AI and knowledge work

    A better blend for retrieval-augmented AI

    BlendFilter combines query enrichment and document filtering to address two common sources of weak retrieval-augmented answers.

    Read the article
  3. Complete abstract from The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm.
    AI safety and society

    Balancing Global and Local Values in Multilingual AI

    A multilingual alignment study reports lower harmful outputs without a measured drop in general response preferences across its test languages.

    Read the article
  4. Complete abstract from AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation.
    Generative AI and automation

    An AI web agent learns to build scrapers

    AutoScraper uses a language model to generate instructions for collecting webpage data. Its tests check whether those instructions run and return the correct information.

    Read the article
  5. Complete abstract from AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments.
    AI and communication research

    AutoPersuade: Evaluating and explaining persuasion with AI

    An AI analysis of pro-vegan messages links argument themes to audience ratings from 5,180 paired comparisons.

    Read the article
  6. Complete abstract from ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models.
    Science and research

    ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models

    Language models generated comparison tables from research papers. Supplying captions and surrounding text helped them identify which features to compare.

    Read the article
  7. Complete abstract from Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis.
    Generative AI in organizations and society

    Language models still miss mental-health comorbidity

    The ANGST benchmark allows social posts to carry depression and anxiety labels together. Even the best tested model struggled with complex cases.

    Read the article
  8. Complete abstract from AgentReview: Exploring Peer Review Dynamics with LLM Agents.
    Science and research

    AgentReview: Exploring Peer Review Dynamics with LLM Agents

    AgentReview simulates conference peer review with language-model agents. Changing reviewer bias changed 37.1% of paper decisions in the simulation.

    Read the article
  9. Complete abstract from ACE: A LLM-based Negotiation Coaching System.
    AI and workplace learning

    ACE: A LLM-based Negotiation Coaching System

    A negotiation coach combines role-play with targeted feedback and reports improved performance across two practice trials.

    Read the article
  10. Complete abstract from ABLE: Personalized Disability Support with Politeness and Empathy Integration.
    Generative AI in organizations and society

    Personalized AI disability support needs more than polite replies

    ABLE trains an AI system to tailor disability-support conversations to user profiles, with politeness and empathy assessed in synthetic dialogues.

    Read the article