paper-with-me

Papers

Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI

2025-01-28 · Carl-Leander Henneking, Claas Beger

Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit principles, limiting interpretability. Constitutional AI (CAI) offers an explicit, rule-based framework for guiding LLM alignment. Building on this, we refine the Inverse Constitutional AI (ICAI) algorithm, which extracts constitutions from preference datasets. By improving principle generation, clustering, and embedding processes, our approach enhances the accuracy and generalizability of extracted principles across synthetic and real-world datasets. Our results highlight the potential of these principles to foster more transparent and adaptable alignment methods, offering a promising direction for future advancements beyond traditional fine-tuning.

📄 PDF Abstract BibTeX arXiv:2501.17112

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cascade Reward Sampling for Efficient Decoding-Time Alignment

2024-06-24 · Bolian Li, Yifan Wang, Anamika Lochab, Ananth Grama 외

Aligning large language models (LLMs) with human preferences is essential for their applications. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that avoids fine-tuning model parame…

Text Generation

Drift: Decoding-time Personalized Alignments with Implicit User Preferences

2025-02-20 · Minbeom Kim, Kang-il Lee, Seongho Joo, Hwaran Lee 외

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. T…

MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention

2024-06-24 · Yuxin Chen, Chen Tang, Chenran Li, Ran Tian 외

Aligning robot behavior with human preferences is crucial for deploying embodied AI agents in human-centered environments. A promising solution is interactive imitation learning from human intervention, where a human exp…

Imitation LearningQ-Learning

Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL

2024-10-16 · Jared Joselowitz, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. Th…

Decision Makingreinforcement-learningReinforcement Learning

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

2025-03-27 · Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag, Soumya Suvra Ghosal 외

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effective technique to align LLMs to human pre…

Model Selection