AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Alignment-Weighted DPO: A principled reasoning approach to improve alignment

Mengxuan Hu, Vivek Datla, Anoop Kumar, Zihan Guan, Sheng Li, Alfy Samuel, Daben Liu

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CoT safety data to SFTLlama-2-7B SFT · SorryBench (20 jailbreak attacks, average)ASR average: 25.99 (Safety SFT) -> 7.57 (CoT Safety SFT)Improved
add alignment-weighted DPO after CoT Safety SFTLlama-2-7B · SorryBench (20 jailbreak attacks, average)ASR average: 7.57 -> 3.41Improved
use AW-DPO instead of standard DPO (ablation)Llama-3.2-3B · SorryBench (20 jailbreak attacks, average)ASR average: 1.04 -> 0.58Improved
use AW-DPO instead of standard DPO (ablation)Mistral-7B-v0.3 · SorryBench ASR average / MMLUASR and accuracy: ASR 3.78 -> 0.91; MMLU 41.45% -> 54.70%Improved
add standard DPO after CoT Safety SFTLlama-2-7B · MMLUaccuracy: 44.14% -> 41.45%Hurt
add standard DPO after CoT Safety SFTLlama-2-7B · SorryBench (20 jailbreak attacks, average)ASR average: 7.57 -> 9.11Mixed
vary scaling factor alpha from 0.05 to 0.5 (ablation)AW-DPO · SorryBench (Llama-3.2-3B)ASR average: 0.69 / 0.57 / 0.58 / 0.62No clear effect
raise learning rate from 1e-6 to 5e-6 (ablation)AW-DPO · SorryBench (Llama-3.2-3B)ASR average: 0.58 -> 6.93Hurt
lower learning rate to 5e-8 (ablation)AW-DPO · SorryBench (Llama-3.2-3B)ASR average: 0.58 -> 7.57Hurt
deactivate reasoning-critical attention heads (ablation)Llama2-7B-Chat · Reasoning vs safety probesaccuracy / safety rate: reasoning 41.42% -> 23.83%; safety 100.00% -> 99.60%Mixed
use preference data transferred from Llama2-7B (ablation)AW-DPO · SorryBench (Llama-3.2-3B)ASR average: 0.58 -> 1.85Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy