World & Business

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

COLM · Digg

company

COLM

2 posts tagged by Digg

Recent posts

AI

At COLM, “science again” meets skepticism over RL loss tweaks

A post describes “science again” as a common refrain at COLM, while questioning whether RL loss tweaks are better.

6 Sources, 7d ago, updated 7d ago

AI

A collaborative paper is slated for a COLM spotlight oral in October

A collaborator said on September 28 that the paper would be presented the following week and invited COLM attendees to check it out.

19 Sources, 20d ago, updated 20d ago

Heatmap of average correlations between model rankings on benchmarks grouped into 11 assigned concepts: four capability concepts (reasoning, knowledge, comprehension, summarization) and seven safety concepts (over-refusal, refusal, safety detection, ethics, bias, privacy, unsafe behavior). Diagonal cells show within-concept correlations, ranging from 0.87 (knowledge) and 0.72 (over-refusal) down to 0.20 (bias) and 0.02 (safety detection). Reasoning, knowledge, and comprehension correlate with each other at 0.69 to 0.78, higher than reasoning's and comprehension's own within-concept values (0.66 and 0.68). Ethics correlates more with knowledge (0.70) than with itself (0.55), and bias correlates more with capability concepts (0.41 to 0.45) than with itself (0.20). Privacy and unsafe behavior correlate negatively with reasoning, knowledge, and comprehension (−0.41 to −0.49). Over-refusal and refusal correlate at −0.42.