Herald:The Biostar Herald for Monday, June 10, 2024
Entering edit mode
9 days ago
Biostar 2.9k

The Biostar Herald publishes user submitted links of bioinformatics relevance. It aims to provide a summary of interesting and relevant information you may have missed. You too can submit links here.

This edition of the Herald was brought to you by contribution from Istvan Albert, and was edited by Istvan Albert,

Journal of Open Source Software: GeneScape: A Python package for gene ontology visualization (joss.theoj.org)

When you have a list of genes and you wonder what gene ontology functions they have in common.

I wrote this tool because I could not find any alternative that did the same.

submitted by: Istvan Albert

x.com (twitter.com)

submitted by: Istvan Albert

x.com (twitter.com)

submitted by: Istvan Albert

[2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models (arxiv.org)

We demonstrate here a dramatic breakdown of function and reasoning capabilities of state-of-the-art models trained at the largest available scales which claim strong function, using a simple, short, conventional common sense problem formulated in concise natural language, easily solvable by humans. The breakdown is dramatic, as models also express strong overconfidence in their wrong solutions, while providing often non-sensical "reasoning"-like explanations akin to confabulations to justify and backup the validity of their clearly failed responses, making them sound plausible. Various standard interventions in an attempt to get the right solution, like various type of enhanced prompting, or urging the models to reconsider the wrong solutions again by multi step re-evaluation, fail. We take these initial observations to the scientific and technological community to stimulate urgent re-assessment of the claimed capabilities of current generation of LLMs,

submitted by: Istvan Albert

Want to get the Biostar Herald in your email? Who wouldn't? Sign up righ'ere: toggle subscription

herald • 193 views

Login before adding your answer.

Traffic: 2049 users visited in the last hour
Help About
Access RSS

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6