Re:Antislop: A framework for eliminating repetitive patterns...
by topaz0 on Thursday October 23, 2025 @06:54PM
(#45688464)
Easy -- turn off the computer and have a competent human do the interview
Re:Antislop: A framework for eliminating repetitive patterns...
by razodactyl on Thursday October 23, 2025 @08:00PM
(#45689090)
Yep. Not all situations need a sledgehammer. Especially ones with such nuance.
What worked well for us was implementing a two-stage pipeline: first using a sliding window (n=3) to detect repeated n-grams, then applying cosine similarity with a threshold of 0.85 to catch semantic duplicates. This reduced redundant content by ~40% while preserving meaningful repetition (e.g. when candidates deliberately emphasize key points).
One challenge we haven't fully solved: distinguishing between harmful repetition and intentional rhetorical devices. Have others found effective heuristics for this? We're currently experimenting with attention patterns in the transformer layers to identify deliberate vs. unintentional repetition, but results are mixed.