Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models

• URL: http://arxiv.org/abs/2312.05503v1
• Date: Sat, 9 Dec 2023 08:25:55 GMT
• Title: Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models
• Authors: Zhou Ziheng, Yingnian Wu, Song-Chun Zhu, and Demetri Terzopoulos (University of California, Los Angeles)
• Abstract summary: We introduce Aligner, a novel. Efficient Fine-Tuning (PEFT) method for aligning multi-billion- parameter-sized Large Language Models (LLMs) We show that Aligner can still perform comparably well to state-of-the-art LLM adaptation methods like LoRA that require millions of parameters.
• Score: 72.26732961610557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Aligner, a novel Parameter-Efficient Fine-Tuning (PEFT) method for aligning multi-billion-parameter-sized Large Language Models (LLMs). Aligner employs a unique design that constructs a globally shared set of tunable tokens that modify the attention of every layer. Remarkably with this method, even when using one token accounting for a mere 5,000 parameters, Aligner can still perform comparably well to state-of-the-art LLM adaptation methods like LoRA that require millions of parameters. This capacity is substantiated in both instruction following and value alignment tasks. Besides the multiple order-of-magnitude improvement in parameter efficiency, the insight Aligner provides into the internal mechanisms of LLMs is also valuable. The architectural features and efficacy of our method, in addition to our experiments demonstrate that an LLM separates its internal handling of "form" and "knowledge" in a somewhat orthogonal manner. This finding promises to motivate new research into LLM mechanism understanding and value alignment.

Related papers

• ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs [27.099331508285108]
  Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains.<n>We present ALTER, a lightweight unlearning framework for LLMs to address both the challenges of knowledge entanglement and unlearning efficiency.
  arXiv  Detail & Related papers  (2026-03-02T12:21:16Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models [7.075648770762989]
  Fine-tuning large language models with low-rank adaptaion (LoRA) is a cost-effective way to incorporate information from a specific dataset.<n>It is often unclear how well the fine-tuned LLM will generalize, i.e., how well it will perform on unseen datasets.<n>We propose Amortized Bayesian Meta-Learning for LoRA (ABMLL) to improve generalization and scales to large models.
  arXiv  Detail & Related papers  (2025-08-19T21:57:59Z)
• Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs [56.76586846269894]
  Multimodal Large Language Models (MLLMs) have achieved success across various domains.<n>Despite its importance, the study of knowledge sharing among domain-specific MLLMs remains largely underexplored.<n>We propose a unified parameter integration framework that enables modular composition of expert capabilities.
  arXiv  Detail & Related papers  (2025-06-30T15:07:41Z)
• Task Specific Pruning with LLM-Sieve: How Many Parameters Does Your Task Really Need? [2.678235552360207]
  Large Language Models (LLMs) are increasingly being adopted for narrow tasks.<n>How many parameters does a task actually need?<n>We present LLM-Sieve, the first comprehensive framework for task-specific pruning of LLMs.
  arXiv  Detail & Related papers  (2025-05-23T20:17:20Z)
• MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models [29.655807841018497]
  We introduce a method for fine-tuning Large Language Models (LLMs) Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. Experimental results, with different datasets and models, demonstrate the proposed method's effectiveness.
  arXiv  Detail & Related papers  (2024-10-20T22:24:40Z)
• MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning [74.43869839954168]
  We propose MTL-LoRA, which retains the advantages of low-rank adaptation while significantly enhancing multi-task learning capabilities. MTL-LoRA augments LoRA by incorporating additional task-adaptive parameters that differentiate task-specific information. This approach enables large language models (LLMs) pre-trained on general corpus to adapt to different target task domains with a limited number of trainable parameters.
  arXiv  Detail & Related papers  (2024-10-12T08:32:26Z)
• 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)
• MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning [105.11844150736536]
  Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. We propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters. Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.
  arXiv  Detail & Related papers  (2024-05-20T15:48:32Z)
• Sub-goal Distillation: A Method to Improve Small Language Agents [21.815417165548187]
  Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks. We propose a method for transferring the performance of an LLM with billions of parameters to a much smaller language model. In ScienceWorld, a challenging and multi-task interactive text environment, our method surpasses standard imitation learning based solely on elementary actions by 16.7%.
  arXiv  Detail & Related papers  (2024-05-04T20:34:06Z)
• LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction [12.611106580612033]
  Large Language Models (LLMs) have demonstrated state-of-the-art performance in numerous attribute extraction tasks. We propose a novel algorithm called LLM-ensemble to ensemble different LLMs' outputs for attribute value extraction. Not only can our proposed method be proven theoretically optimal, but it also ensures efficient computation, fast convergence, and safe deployment.
  arXiv  Detail & Related papers  (2024-02-29T23:03:19Z)
• RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation [9.606111709136675]
  We present RA-Rec, an efficient ID representation framework for LLM-based recommendation. RA-Rec substantially outperforms current state-of-the-art methods, achieving up to 3.0% absolute HitRate@100 improvements.
  arXiv  Detail & Related papers  (2024-02-07T02:14:58Z)
• Small LLMs Are Weak Tool Learners: A Multi-LLM Agent [73.54562551341454]
  Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs. We propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability.
  arXiv  Detail & Related papers  (2024-01-14T16:17:07Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)

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.