Post #1499812
2026-04-15 15:07 UTC
@malteengeler
I think the lack of hallucination refers to the sources. It doesn't make up references, rather it gives you full access to the original sources.
The quality summaries across papers is likely to vary, but this is like complaining about abstracts not giving you full details. Of course not, if you want that, read the paper.
This interface provides a new access to them, the same way an abstract provides you with some idea whether it's worth reading the full paper.
Replies (2)
-
@malteengeler@legal.social 2026-04-15 15:12
@festal But the abstract is created via LLMs the same way Google AI Overview etc is, right? I don't see how this beats the allegations of "no hallucinations". It is of course better to not also use the LLM to synthesize the text that humans understand as "sources". But it is still using stochastic word synthesis for the abstract, no?
-
@Rainer_Rehak@mastodon.bits-und-baeume.org 2026-04-15 15:20
@festal @malteengeler I apparently have a different understanding of an abstract, as it is a clearly defined type of text (intro, background, question, approach, findings, implications, contribution), but #LLMs do not work like that. On the other hand, perplexity, consensus and semantic scholar sometimes really do work well. ;)