ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation

• URL: http://arxiv.org/abs/2405.13578v2
• Date: Mon, 30 Dec 2024 07:25:13 GMT
• Title: ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
• Authors: Weilong Dong, Xinwei Wu, Renren Jin, Shaoyang Xu, Deyi Xiong,
• Abstract summary: ConTrans is a novel framework that enables weak-to-strong alignment transfer via concept transplantation.<n>Experiment results validate the effectiveness of both inter-LLM-family and intra-LLM-family concept transplantation.
• Score: 35.95755927728259
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring large language models (LLM) behave consistently with human goals, values, and intentions is crucial for their safety but yet computationally expensive. To reduce the computational cost of alignment training of LLMs, especially for those with a huge number of parameters, and to reutilize learned value alignment, we propose ConTrans, a novel framework that enables weak-to-strong alignment transfer via concept transplantation. From the perspective of representation engineering, ConTrans refines concept vectors in value alignment from a source LLM (usually a weak yet aligned LLM). The refined concept vectors are then reformulated to adapt to the target LLM (usually a strong yet unaligned base LLM) via affine transformation. In the third step, ConTrans transplants the reformulated concept vectors into the residual stream of the target LLM. Experiments demonstrate the successful transplantation of a wide range of aligned concepts from 7B models to 13B and 70B models across multiple LLMs and LLM families. Remarkably, ConTrans even surpasses instruction-tuned models in terms of truthfulness. Experiment results validate the effectiveness of both inter-LLM-family and intra-LLM-family concept transplantation. Our work successfully demonstrates an alternative way to achieve weak-to-strong alignment generalization and control.

Related papers

• Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts [24.990218468155383]
  This work explores the intricate relationships between concept representations across different Large Language Models (LLMs) We introduce a linear transformation method to bridge these representations, drawing an intriguing parallel to Plato's Allegory of the Cave. A weak-to-strong transferability exists between LLM concept representations, whereby SVs extracted from smaller LLMs can effectively control the behavior of larger LLMs.
  arXiv  Detail & Related papers  (2025-01-02T11:56:59Z)
• Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning [53.685764040547625]
  Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. This work provides a fine mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities.
  arXiv  Detail & Related papers  (2024-11-04T15:54:32Z)
• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
  We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM. We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings [7.957874169275548]
  Training-free embedding methods directly leverage pretrained large language models (LLMs) to embed text. We propose a novel method, which uses LLMs to generate diverse transformations of a sentence that preserve its meaning.
  arXiv  Detail & Related papers  (2024-10-18T17:36:53Z)
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs [40.74693126923826]
  Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. Training adapters with image-level supervision often results in significant misalignment. We introduce Supervised Embedding Alignment (SEA), a token-level alignment method that leverages vision-language pre-trained models.
  arXiv  Detail & Related papers  (2024-08-21T17:58:02Z)
• Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement [72.97553348776425]
  We make a pioneering effort to broaden the applicability of merging techniques from FT to PT LLMs. We introduce an approach based on WeIght DisENtanglement (WIDEN) to effectively extend the merging scope. We merge Qwen1.5-Chat (an FT LLM with instruction-following skills) with Sailor (a PT LLM with multilingual abilities) across 7B and 14B model scales.
  arXiv  Detail & Related papers  (2024-08-06T10:46:46Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model [22.870512676002463]
  This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators. Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs. Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.
  arXiv  Detail & Related papers  (2023-10-24T03:08:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.