Highlighting LLM-Generated Content in Search Results: Do We Need a New Link Attribute?

Daniel Griffin ·

An Oct 5 article from Will Knight in Wired discusses my Claude Shannon "hallucination" test: Chatbot Hallucinations Are Poisoning Web Search

A round-up here: Can you write about examples of LLM hallucination without poisoning the web?

Introduction

Large language models (LLMs)—statistical machines that are trained to generate natural language—sometimes output content that is unfounded and untrue.
While interacting with these models can be entertaining and even spark creativity and spur on curiosity, it becomes problematic when readers can't tell what is real.
This differs from a fictional story that's clearly marked as such, like a fairy tale that begins with 'Once upon a time.'
These are often referred to as 'hallucinations'. Some debate the term's suitability (preferring the language to be more descriptive (undesired fabrication, as in "they fabricate nonexistent but seemingly factual text that misleads and can have catastrophic consequences if not corrected") or more evocative and less euphemistic ("bullshit")).

For many who work with or use LLMs today, that is an ever-running concern. There are significant research and engineering efforts focused on addressing the problematic hallucinations, including fine-tuning, automating validation (like Bard's new "Double-check response feature", retrieving relevant contexts and adding to prompts before generation (in various retrieval augmented generation (RAG) approaches) and the sources-cited features in many generative search systems).

The Problem

The problem I'm looking at in this post is not the hallucinations themselves, but how search engines sometimes misrepresent content from LLM chats. For example, recently Google reproduced (or regurgitated) an output from an LLM as the featured snippet for the query [can you melt eggs]. There was no direct indication to a user that content Google promoted was generated from an LLM.

There are plenty of interesting questions in regards to {% include svg-bot-ixn-icon.html %}what an ideal search system might answer for this query.

My Experience

I have been writing about my explorations with these systems and my own work has played a role in spreading decontextualized falsehoods.

First, when I entered my 'Claude Shannon hallucination test' query into Bing, the search engine returned an LLM generated chat (that I'd linked to) as a featured snippet, devoid of the context I'd provided and both Bing


and Google


returned multiple such results without any indication to an uninformed reader that the results were generated by an interaction between a user and an LLM.

Second, {% include_cached svg-clipboard-icon.html %}Perplexity AI, a generative search engine, cited to my page about the hallucinations as evidence for the nonexistent publication. Perplexity AI mistakenly treated my critique about the LLM hallucinations re a fictitious publication from Claude Shannon as genuine information. (When I originally ran Perplexity AI on this test, it avoided hallucination (while in its premium 'Copilot' mode).)

I want to continue to write about these problematic statements, and even link to them for others to see for themselves. But I don't want to lend the outputs legitimacy. So I'm still grappling with the challenge of how to write about examples of LLM chats without 'poisoning the well'. ('Poisoning the well' refers to sharing this problematic information in ways that might be scooped up by search engines and presented to users.

Proposed Actions

In my initial attempt to write about my 'Claude Shannon hallucination test', I had a clear note at the top of the page and inserted ClaimReview structured data as well (a schema.org type: "A fact-checking review of claims made (or reported) in some creative work"; see my discussion here). Since seeing the failures above, I've tapped into more advanced features of the ClaimReview schema. By integrating direct links to individual pages within the structured data, I aim to provide clearer differentiation. We'll see if that makes a difference.

I'll also introduce a custom rel attribute, bot-ixn (short for 'bot interaction') for indicated pages that primarily included unedited interactions with LLMs and other sources of natural language generation. While I primarily intend this for my own use, it might inspire others to adopt or adapt the idea. I hope this might help a few folks pause to consider this broader question. I will be sort of role-playing a response to feel it out. I can use this to mark all my links leading to such content and to facilitate instructive styling for human readers.

See: github.com/danielsgriffin/bot-ixn

Example:

{% include svg-bot-ixn-icon.html %}Interacting with Google's Bard on this topic

Seeking Input

What strategies are others adopting? Are there alternative methods or attributes that others are exploring to differentiate LLM chat content?

Review

  • LLMs can output content that is problematic in various ways.
  • It may still be valuable to link to and search for such content.
  • There does not seem to be approaches designed to address marking out such content.
  • I've previously tried the ClaimReview schema (see my initial attempt here).
  • I'll be trying a custom rel attribute: bot-ixn.
standing-querieshallucination

Daniel Griffin