Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.
The e2e dataset: New challenges for end-to-end generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
This paper describes the E2E data, a new dataset for training end-to-end, data-driven natural language generation systems in the restaurant domain, which is ten times bigger than existing, frequently used datasets in this area. The E2E dataset poses new challenges: (1) its human reference texts show more lexical richness and syntactic variation, including discourse phenomena; (2) generating from this set requires content selection. As such, learning from this dataset promises more natural, varied and less template-like system utterances. We also establish a baseline on this dataset, which illustrates some of the difficulties associated with this data.
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.
LMNet connects stripped LLMs as nodes with trainable seq2seq edges for dense vector exchange, supporting supervision-efficient learning through differentiable communication.
AdaPreLoRA pairs the Adafactor diagonal Kronecker preconditioner on the full weight matrix with a closed-form factor-space solve that selects the update minimizing an H_t-weighted imbalance, yielding competitive results on GPT-2, Mistral-7B, Qwen2-7B and diffusion personalization tasks.
citing papers explorer
-
LoRA: Low-Rank Adaptation of Large Language Models
Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.
-
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.
-
Language Model Networks: Supervision-Efficient Learning through Dense Communication
LMNet connects stripped LLMs as nodes with trainable seq2seq edges for dense vector exchange, supporting supervision-efficient learning through differentiable communication.
-
AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
AdaPreLoRA pairs the Adafactor diagonal Kronecker preconditioner on the full weight matrix with a closed-form factor-space solve that selects the update minimizing an H_t-weighted imbalance, yielding competitive results on GPT-2, Mistral-7B, Qwen2-7B and diffusion personalization tasks.