paper-with-me

홈 › Papers

Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation

2022-09-22 · Xingdi Yuan, Tong Wang, Yen-Hsiang Wang, Emery Fine, Rania Abdelghani, Pauline Lucas, Hélène Sauzéon, Pierre-Yves Oudeyer

Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation. A common practice to improve generation diversity is to sample multiple outputs from the model. However, there lacks a simple and robust way of selecting the best output from these stochastic samples. As a case study framed in the context of question generation, we propose two prompt-based approaches to selecting high-quality questions from a set of LLM-generated candidates. Our method works under the constraints of 1) a black-box (non-modifiable) question generation model and 2) lack of access to human-annotated references -- both of which are realistic limitations for real-world deployment of LLMs. With automatic as well as human evaluations, we empirically demonstrate that our approach can effectively select questions of higher qualities than greedy generation.

📄 PDF Abstract BibTeX arXiv:2209.11000

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityQuestion GenerationQuestion-GenerationText Generation

Similar Papers 제목 키워드 기반

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

2026-03-05 · Amirabbas Afzali, Myeongho Jeon, Maria Brbic arxiv

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether…

RECOST: External Knowledge Guided Data-efficient Instruction Tuning

2024-02-27 · Qi Zhang, Yiming Zhang, Haobo Wang, Junbo Zhao

In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to re…

DiversityRe-Ranking

Improving Causal Effect Estimation of Weighted RegressionBased Estimator using Neural Networks

2021-10-28 · Plabon Shaha, Talha Islam Zadid, Ismat Rahman, Md. Mosaddek Khan

Estimating causal effects from observational data informs us about which factors are important in an autonomous system, and enables us to take better decisions. This is important because it has applications in selecting …

regression

In-Context Learning Demonstration Selection via Influence Analysis

2024-02-19 · Vinay M. S., Minh-Hao Van, Xintao Wu

Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities, enabling few-shot learning without the need for gradient updates. Despite its advantages, the effectiveness of ICL heavily depends…

Few-Shot LearningIn-Context Learning

Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study

2024-12-24 · Xuefeng Jiang, Lvhua Wu, Sheng Sun, Jia Li 외

Code vulnerability detection (CVD) is essential for addressing and preventing system security issues, playing a crucial role in ensuring software security. Previous learning-based vulnerability detection methods rely on …

Vulnerability Detection