Tag: Alignment
All the articles with the tag "Alignment".
-
Reverse Preference Optimization for Complex Instruction Following
Published: at 11:44 AM
85.20 🤔本文提出逆向偏好优化（RPO）方法，通过动态反转指令中未满足的约束消除偏好对噪声，在多轮复杂指令跟随任务上显著优于DPO基线，并在70B模型上超越GPT-4o。
-
From Distributional to Overton Pluralism: Investigating Large Language Model Alignment
Published: at 11:16 AM 85.12 🤔本文通过分析对齐前后LLM输出分布的变化，揭示了对齐虽减少分布性多元化但通过更长响应实现奥弗顿多元化，且基础模型通过上下文学习可有效模仿对齐模型行为，支持表面对齐假说。
-
Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
Published: at 11:45 AM 85.12 🤔本文提出残差对齐模型（RAM），通过重要性采样分离对齐模块，实现高效的序列级训练和令牌级解码，在多个对齐任务中显著提升性能并降低资源成本。
-
HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models
Published: at 04:27 PM 78.97 🤔本文提出Head-Specific Intervention (HSI)方法，通过针对特定注意力头的激活干预，成功诱导Llama 2模型在AI协调行为上绕过安全对齐，效果优于监督微调和其它干预策略。
-
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
Published: at 11:14 AM 76.90 🤔This paper introduces Latent Preference Coding (LPC), a framework that uses discrete latent codes to model multifaceted human preferences, consistently improving the performance of offline alignment algorithms like DPO, SimPO, and IPO across multiple LLMs and benchmarks.