PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2511.21285/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark — mentioned by hereme888https://news.ycombinator.com/item?id=46098373urn:hackerpapers:mention:2511.21285:46098373Sun, 30 Nov 2025 17:04:15 GMT<p>recent results like PEFT-Bench (arxiv.org/abs/2511.21285) found that while SFT is efficient for formatting, it actually degraded Llama-3-8B&#x27;s reasoning on math and code tasks compared to the base model. So is RL required to preserve those logic circuits? There seems to be a trade-off in compute-efficiency and format vs intelligence</p><p><a href="https://hackerpaper.kaipfister.de/p/2511.21285/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL