paper-with-me

Papers

Investigating the Effectiveness of HyperTuning via Gisting

2024-02-26 · Jason Phang

Gisting (Mu et al., 2023) is a simple method for training models to compress information into fewer token representations using a modified attention mask, and can serve as an economical approach to training Transformer-based hypernetworks. We introduce HyperLlama, a set of Gisting-based hypernetworks built on Llama-2 models that generates task-specific soft prefixes based on few-shot inputs. In experiments across P3, Super-NaturalInstructions and Symbol Tuning datasets, we show that HyperLlama models can effectively compress information from few-shot examples into soft prefixes. However, they still underperform multi-task fine-tuned language models with full attention over few-shot in-context examples. We also show that HyperLlama-generated soft prefixes can serve as better initializations for further prefix tuning. Overall, Gisting-based hypernetworks are economical and easy to implement, but have mixed empirical performance.

📄 PDF Abstract BibTeX arXiv:2402.16817

Code (1)

zphang/hyperllama 공식 구현

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

HyperTuning: Toward Adapting Large Language Models without Back-propagation

2022-11-22 · Jason Phang, Yi Mao, Pengcheng He, Weizhu Chen

Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based optimization. We propose HyperTuning, a n…

Language ModelingLanguage Modellingparameter-efficient fine-tuning

Long Context In-Context Compression by Getting to the Gist of Gisting

2025-04-11 · Aleksandar Petrov, Mark Sandler, Andrey Zhmoginov, Nolan Miller 외

Long context processing is critical for the adoption of LLMs, but existing methods often introduce architectural complexity that hinders their practical adoption. Gisting, an in-context compression method with no archite…

Decoder

Exploring Gap Filling as a Cheaper Alternative to Reading Comprehension Questionnaires when Evaluating Machine Translation for Gisting

2018-09-02 · WS 2018 10 · Mikel L. Forcada, Carolina Scarton, Lucia Specia, Barry Haddow 외

A popular application of machine translation (MT) is gisting: MT is consumed as is to make sense of text in a foreign language. Evaluation of the usefulness of MT for gisting is surprisingly uncommon. The classical metho…

Machine TranslationReading ComprehensionSentenceTranslation

Learning to Compress Prompts with Gist Tokens

2023-04-17 · NeurIPS 2023 11 · Jesse Mu, Xiang Lisa Li, Noah Goodman

Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally ineff…

Decoder

Self-learning locally-optimal hypertuning using maximum entropy, and comparison of machine learning approaches for estimating fatigue life in composite materials

2022-10-19 · Ismael Ben-Yelun, Miguel Diaz-Lago, Luis Saucedo-Mora, Miguel Angel Sanz 외

Applications of Structural Health Monitoring (SHM) combined with Machine Learning (ML) techniques enhance real-time performance tracking and increase structural integrity awareness of civil, aerospace and automotive infr…

Self-LearningStructural Health Monitoring