Challenge: Recent work aimed to improve task performance of large language models by rewriting or tuning them manually, but manual rewrite is time-consuming and requires subjective interpretation.
Approach: They propose a gradient-free, edit-based search approach for improving task instructions for large language models.
Outcome: The proposed approach outperforms manual rewriting and purely example-based prompts while allowing for API-based tuning.

Similar Papers

Self-Instruct: Aligning Language Models with Self-Generated Instructions (2023.acl-long)

Copied to clipboard

Challenge: Large “instruction-tuned” language models depend heavily on human-written instruction data . this limited quantity, diversity, and creativity hinders the generality of the tuned model .
Approach: They propose a framework for improving instruction-following capabilities of pretrained language models by bootstrapping off their own generations.
Outcome: The proposed framework outperforms existing public instruction datasets by 5% . it generates instructions, input, and output samples, then filters invalid or similar ones .
Automatic Prompt Optimization with “Gradient Descent” and Beam Search (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort.
Approach: They propose an algorithm that uses numerical gradient descent to automatically improve prompts by rewriting vague task descriptions into more precise annotation instructions.
Outcome: The proposed algorithm outperforms previous methods and improves performance on three benchmark NLP tasks and the novel problem of LLM jailbreak detection.
Reliable Gradient-free and Likelihood-free Prompt Tuning (2023.findings-eacl)

Copied to clipboard

Challenge: Large pre-trained language models are often offered as black-box APIs due to privacy or commercial constraints.
Approach: They propose to tune the soft prompts without requiring gradient computation and extend the model to include a distribution over prompts.
Outcome: The proposed methods are competitive with gradient-based approaches with full access to the PLM.
InstructCoder: Instruction Tuning Large Language Models for Code Editing (2024.acl-srw)

Copied to clipboard

Challenge: InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing.
Approach: They propose to use Large Language Models to edit code based on user instructions . they use a dataset to adapt LLMs to general-purpose code editing .
Outcome: The proposed model can significantly improve code editing performance compared to proprietary models . the proposed model is based on a human-written execution-based benchmark .
Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning (2023.findings-acl)

Copied to clipboard

Challenge: Prompting has gained tremendous attention as an efficient method for the adaptation of large-scale language models.
Approach: They propose a regularization method that guides a prompt to produce a task context properly.
Outcome: The proposed method improves prediction performance in a zero-shot in-context learning setting without demonstration examples for in-constitu learning.
Automated Few-Shot Classification with Instruction-Finetuned Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing few-shot learning approaches combine language models with prompts, but they often require domain knowledge and substantial guesswork.
Approach: They propose a method to eliminate the need for handcrafted prompts by generating two distinct, semantically meaningful class descriptions and a selection mechanism via cross-validation.
Outcome: The proposed method outperforms state-of-the-art few-shot learning methods over 12 datasets, spanning 8 classification tasks.
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning (2022.emnlp-main)

Copied to clipboard

Challenge: Instruction tuning is emerging in NLP, but has not been explored for dialogue-related tasks.
Approach: They propose an instruction tuning framework for dialogue that leverages natural language instructions with language models to induce zero-shot generalization on unseen tasks.
Outcome: The proposed framework enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection.
Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have led to remarkable achievements across a variety of NLP tasks.
Approach: They propose a taxonomy of automatic prompt optimization methods that explore and improve prompts with minimal human oversight.
Outcome: The proposed methods can explore and improve prompts with minimal human oversight.
HINT: Hypernetwork Instruction Tuning for Efficient Zero- and Few-Shot Generalisation (2023.acl-long)

Copied to clipboard

Challenge: Recent NLP models have shown the remarkable ability to generalise ‘zero-shot’ to new tasks using only natural language instructions as guidance.
Approach: They introduce Hypernetworks for INstruction Tuning (HINT) which converts task instructions and examples into parameter-efficient modules inserted into an underlying model using a pretrained text encoder.
Outcome: The proposed models outperform strong state-of-the-art models by over 10% when controlling for compute.
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach: They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome: The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations