← back to paper

Review history

arxiv: 2509.05553 · 2 revisions

Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   127466 ms 11686 in 15779 out 2026-08-15T16:23:14.377929+00:00
2. 2026-08-05 REJECT MODERATE v1.3.0-alltime-deepseek novelty 4.0
   155596 ms 11660 in 15134 out 2026-08-05T05:20:36.451475+00:00