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 EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records.
    Generative AI in organizations and society

    Code feedback helps LLMs query complex health records

    EHRAgent uses generated code, medical context and execution feedback to answer multi-table questions in three electronic health record datasets.

    Read the article
  2. Complete abstract from Towards Measuring and Modeling “Culture” in LLMs: A Survey.
    AI and society

    Culture Needs More Than One Language-model Score

    A survey of 90 papers finds that culture is usually measured through proxies, leaving important contexts and lived experience outside the test.

    Read the article
  3. Complete abstract from CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading.
    Generative AI in organizations and society

    AI crypto agents combine market data, news and reflection

    CryptoTrade combines blockchain activity, market indicators and financial news. Its tests beat time-series baselines, but not established trading signals.

    Read the article
  4. Complete abstract from Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering.
    AI and commerce

    AI Answers Cross-market Product Questions Across 11 Languages

    A multilingual benchmark tests whether product reviews and questions from one marketplace can help answer questions in another.

    Read the article
  5. Complete abstract from “They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations.
    AI governance and society

    The subtle harms hidden in AI conversations

    CHAST evaluates seven forms of social harm in simulated hiring dialogues and finds that many tested models produced biased views in neutral-sounding language.

    Read the article
  6. Complete abstract from ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures.
    Generative AI in organizations and society

    Climate-report retrieval benchmarks expose a knowledge gap for AI

    ClimRetrieve measures whether search systems find the evidence a sustainability analyst needs in company climate reports.

    Read the article
  7. 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
  8. 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
  9. 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
  10. 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