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
The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?
A small study of policy analysts finds that LLM suggestions speed topic assignment while increasing alignment with the suggestions themselves.
Read the article
LitSearch: Benchmarking AI retrieval of scientific literature
On 597 literature-search questions, an AI retriever outperformed keyword search. Using GPT-4o to reorder results improved retrieval further.
Read the article
When should an AI answer or refuse?
Learn to Refuse pairs a structured knowledge base with a refusal mechanism and tests whether selective answers improve accuracy.
Read the article
What legal knowledge can language models show?
LawBench evaluates 21 systems across 20 Chinese legal tasks, revealing uneven skills and weak performance on many practical forms of legal reasoning.
Read the article
Knowledge checks can help reduce AI errors
Knowledge Consistent Alignment tests what a model knows before fine-tuning and compares several ways to handle gaps.
Read the article
When a Language Model’s Knowledge Collides
A survey separates conflicts between prompts, retrieved sources and model memory—and explains why resolving them is context-dependent.
Read the article
In-Context Learning in Language Models Has Many Moving Parts
A survey and benchmark study show why examples, scoring choices and model differences all affect in-context learning.
Read the article
How Researchers Define and Test LLM Factuality
A survey separates factuality from related ideas and explains why checking open-ended model answers remains difficult.
Read the article
Do AI assistants shift political views?
An experiment with 935 registered US voters found that political conversations with three AI models coincided with changed candidate support for some participants.
Read the article
HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs
Researchers used GPT-4 to label 874 personal stories. Readers reported more empathy for stories with greater character development and more plot events.
Read the article
