“Inoculation Adapters Improve Upon Inoculation Prompting” by Maxime Riché, Daniel Tan, Vili Kohonen, nielsrolf

episode

LessWrong (30+ Karma) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

More from LessWrong (30+ Karma)

“Claude Opus 4.5 Achieves 50%-Time Horizon Of Around 4 hrs 49 Mins” by Michaël Trazzi 3 min · 20 Dec 2025

All episodes from LessWrong (30+ Karma) →

Report any issue

Source

Recorded17 Jul 2026

Publisherfeeds.type3.audio ↗

Handlerec:19327556

Show notes

This is a link post for the paper preprint: Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors from the Center on Long-Term Risk. Selective generalization. Training can teach desired and undesired traits at once. Selective generalization aims to preserve the generalization of desired traits while preventing the generalization of undesired ones. For example, RL environments may teach a model useful capabilities and a propensity to reward hack, and AI developers would like only the capabilities to generalize. Inoculation adapters (IA) work similarly to inoculation prompting (IP), but instead of eliciting the undesired trait via prompting, we use a LoRA carrying the undesired trait during training. IA improves on IP in: Achieving stronger suppression of undesired traits (e.g., emergent misalignment).Being effective against new capabilities and hard-to-elicit traits, unlike inoculation prompting.Creating substantially fewer surprising backdoors under our probes. A family of methods. On average, IA outperforms other baselines, such as preventative steering and concept-ablation fine-tuning, in suppressing undesired traits. In terms of retention of the desired trait, (vanilla) IA performs worse than these baselines. We introduce gated IA (GIA) and complementary-gated IA (CGIA), which are in the same family of methods but achieve similar or [...] ---Outline:(05:26) What is an inoculation adapter (IA)?(06:41) Other relevant content in the preprint(07:12) What inoculation adapters do not solve:(08:02) Related work --- First published: July 17th, 2026 Source: https://www.lesswrong.com/posts/qd3qhxgEmQAXR2ZK5/inoculation-adapters-improve-upon-inoculation-prompting --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.