LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates

• URL: http://arxiv.org/abs/2503.16334v1
• Date: Thu, 20 Mar 2025 16:55:26 GMT
• Title: LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates
• Authors: Ying Shen, Lifu Huang,
• Abstract summary: We propose LLMBRACES, a method that computes relevance scores associated with value vectors in FFN layers.<n>By optimizing sub-update contributions, LLMBRACES refines the prediction process, leading to more accurate and reliable outputs.<n>LLMBRACES excels in sentiment-controlled generation and toxicity reduction, highlighting its potential for flexible, controlled text generation across applications.
• Score: 27.022532404557264
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent findings reveal that much of the knowledge in a Transformer-based Large Language Model (LLM) is encoded in its feed-forward (FFN) layers, where each FNN layer can be interpreted as the summation of sub-updates, each corresponding to a weighted column vector from the FFN's value parameter matrix that often encodes human-interpretable concepts. In light of this, we hypothesize that model performance and behaviors can be further enhanced and controlled by modulating the contributions of these sub-updates based on their relevance to the input or target output style, and propose LLMBRACES, a novel and efficient method that computes relevance scores associated with value vectors in FFN layers and leverages these scores to dynamically adjust the contribution of sub-updates. By optimizing sub-update contributions, LLMBRACES refines the prediction process, leading to more accurate and reliable outputs, much like a 'brace' providing support and stability. Moreover, LLMBRACES can be extended to support conditional control over generation characteristics, such as sentiment, thereby offering fine-grained steering of LLM outputs. Extensive experiments on various LLMs-including Qwen2.5-1.5B, Llama2-7B, and Llama3-8B-demonstrate that LLMBRACES outperforms baseline approaches in both fine-tuning and zero-shot settings while requiring significantly fewer tunable parameters, up to 75% fewer compared to LoRA. Furthermore, LLMBRACES excels in sentiment-controlled generation and toxicity reduction, highlighting its potential for flexible, controlled text generation across applications.

Related papers

• GEM: Empowering LLM for both Embedding Generation and Language Understanding [11.081595808236239]
  We propose Generative Embedding large language Model (GEM) to generate high-quality text embeddings.<n>Our method inserts new special token(s) into a text body, and generates summarization embedding of the text by manipulating the attention mask.<n>Our results indicate that our approach can empower LLMs with state-of-the-art text embedding capabilities while maintaining their original NLP performance.
  arXiv  Detail & Related papers  (2025-06-04T18:02:07Z)
• Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration [13.824354003574843]
  Bohdi is a synthetic-data-only heterogeneous Large Language Model (LLM) fusion framework.<n>By organization of knowledge domains into a hierarchical tree structure, Bohdi enables automatic domain exploration and multi-domain data generation.<n>Bohdi significantly outperforms existing baselines on multiple target LLMs.
  arXiv  Detail & Related papers  (2025-06-04T17:01:38Z)
• Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator [5.985414012866983]
  Large language model (LLM) pruning with fixed N:M structured sparsity limits the expressivity of the sparse model. We present a flexible layer-wise outlier-density-aware N:M sparsity (FLOW) selection method. We then introduce a flexible, low-overhead digital compute-in-memory architecture (FlexCiM)
  arXiv  Detail & Related papers  (2025-04-19T17:47:01Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting [20.07438999071414]
  Large Language Models (LLMs) are rapidly transforming the landscape of digital content creation.<n>We present FD-Dataset, a comprehensive bilingual fingerprinting benchmark comprising 90,000 text samples from 20 famous proprietary and open-source LLMs.<n>We also present FDLLM, a novel fingerprinting method that leverages parameter-efficient Low-Rank Adaptation (LoRA) to fine-tune a foundation model.
  arXiv  Detail & Related papers  (2025-01-27T13:18:40Z)
• Beyond Inter-Item Relations: Dynamic Adaption for Enhancing LLM-Based Sequential Recommendation [83.87767101732351]
  Sequential recommender systems (SRS) predict the next items that users may prefer based on user historical interaction sequences. Inspired by the rise of large language models (LLMs) in various AI applications, there is a surge of work on LLM-based SRS. We propose DARec, a sequential recommendation model built on top of coarse-grained adaption for capturing inter-item relations.
  arXiv  Detail & Related papers  (2024-08-14T10:03:40Z)
• Applying RLAIF for Code Generation with API-usage in Lightweight LLMs [15.366324461797582]
  Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (1B parameters) LLMs.
  arXiv  Detail & Related papers  (2024-06-28T17:16:03Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models [0.0]
  Large Language Models (LLMs) have shown exceptional performance in text processing. This paper proposes a novel approach to training LLMs using knowledge transfer from a random forest (RF) ensemble. We generate outputs for fine-tuning, enhancing the model's ability to classify and explain its decisions.
  arXiv  Detail & Related papers  (2024-06-07T13:31:51Z)
• Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes [57.62036621319563]
  We introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the low-data regime. We demonstrate the superior performance of CLLM in the low-data regime compared to conventional generators.
  arXiv  Detail & Related papers  (2023-12-19T12:34:46Z)
• 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)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• 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.