LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
- URL: http://arxiv.org/abs/2402.11251v1
- Date: Sat, 17 Feb 2024 11:18:22 GMT
- Title: LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
- Authors: Siyin Wang, Shimin Li, Tianxiang Sun, Jinlan Fu, Qinyuan Cheng,
Jiasheng Ye, Junjie Ye, Xipeng Qiu, Xuanjing Huang
- Abstract summary: Large Language Models (LLMs) employ diverse decoding strategies to control the generated text.
Are LLMs conscious of the existence of these decoding strategies and capable of regulating themselves?
We propose a novel text generation paradigm termed Hyperparameter Aware Generation (HAG)
- Score: 88.69052513433603
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In the realm of Large Language Models (LLMs), users commonly employ diverse
decoding strategies and adjust hyperparameters to control the generated text.
However, a critical question emerges: Are LLMs conscious of the existence of
these decoding strategies and capable of regulating themselves? The current
decoding generation process often relies on empirical and heuristic manual
adjustments to hyperparameters based on types of tasks and demands. However,
this process is typically cumbersome, and the decoding hyperparameters may not
always be optimal for each sample. To address the aforementioned challenges, we
propose a novel text generation paradigm termed Hyperparameter Aware Generation
(HAG). By leveraging hyperparameter-aware instruction tuning, the LLM
autonomously determines the optimal decoding strategy and configs based on the
input samples, enabling self-regulation. Our approach eliminates the need for
extensive manual tuning, offering a more autonomous, self-regulate model
behavior. Experimental results spanning six datasets across reasoning,
creativity, translation, and mathematics tasks demonstrate that
hyperparameter-aware instruction tuning empowers the LLMs to self-regulate the
decoding strategy and hyperparameter. HAG extends the current paradigm in the
text generation process, highlighting the feasibility of endowing the LLMs with
self-regulate decoding strategies.
Related papers
- Adaptive Draft-Verification for Efficient Large Language Model Decoding [24.347886232342862]
Large language model (LLM) decoding involves generating a sequence of tokens based on a given context.
The typical autoregressive decoding method requires a separate forward pass through the model for each token generated.
We introduce ADED, which accelerates LLM decoding without requiring fine-tuning.
arXiv Detail & Related papers (2024-06-27T22:20:39Z) - Adaptable Logical Control for Large Language Models [68.27725600175013]
Ctrl-G is an adaptable framework that facilitates tractable and flexible control of model generation at inference time.
We show that Ctrl-G, when applied to a TULU2-7B model, outperforms GPT3.5 and GPT4 on the task of interactive text editing.
arXiv Detail & Related papers (2024-06-19T23:47:59Z) - Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
We introduce the framework of verbalized machine learning (VML)
VML constrains the parameter space to be human-interpretable natural language.
We conduct several studies to empirically evaluate the effectiveness of VML.
arXiv Detail & Related papers (2024-06-06T17:59:56Z) - 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) - Large Language Model Agent for Hyper-Parameter Optimization [30.560250427498243]
We introduce a novel paradigm leveraging Large Language Models (LLMs) to automate hyperparameter optimization across diverse machine learning tasks.
AgentHPO processes the task information autonomously, conducts experiments with specific hyper parameters, and iteratively optimize them.
This human-like optimization process largely reduces the number of required trials, simplifies the setup process, and enhances interpretability and user trust.
arXiv Detail & Related papers (2024-02-02T20:12:05Z) - Prompt Highlighter: Interactive Control for Multi-Modal LLMs [50.830448437285355]
This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation.
We introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation.
We find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs.
arXiv Detail & Related papers (2023-12-07T13:53:29Z) - Mixture of Soft Prompts for Controllable Data Generation [21.84489422361048]
Mixture of Soft Prompts (MSP) is proposed as a tool for data augmentation rather than direct prediction.
Our method achieves state-of-the-art results on three benchmarks when compared against strong baselines.
arXiv Detail & Related papers (2023-03-02T21:13:56Z) - Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs.
Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
arXiv Detail & Related papers (2023-02-22T17:44:15Z)
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.