This study explored when and how Large Language Models (LLMs) expose the human user to biased content, and quantified the extent of biased information. E.g. they fed the LLMs prompts and asked it to summarise, and then compared how the LLMs changed the content, context, hallucinated, or changed the sentiment. Providing context: ·         LLMs “are… Continue reading How Much Content Do LLMs Generate That Induces Cognitive Bias in Users?

Here’s a critical response paper to yesterday’s “ChatGPT is bullshit” article from Hicks et al. Links to both articles below. Some core arguments: ·        Hick’s characterises LLMs as bullshitters, since LLMs “”cannot themselves be concerned with truth,” and thus “everything they produce is bullshit” ·        Hicks et al. rejects anthropomorphic terms such as hallucination or confabulation, since… Continue reading Cut the crap: a critical response to “ChatGPT is bullshit”

This was pretty interesting – it compared GPT-4o to people in extracting takeaways from visualised data. They were also interested in how well the LLM could simulate human respondents/responses. Note that the researchers are primarily interested in whether the GPT-4o model acts as a suitable proxy for human responses – they recognise there are other… Continue reading LLMs Are Not Reliable Human Proxies to Study Affordances in Data Visualizations