Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference

• URL: http://arxiv.org/abs/2410.08289v1
• Date: Thu, 10 Oct 2024 18:21:00 GMT
• Title: Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference
• Authors: William Thorne, Ambrose Robinson, Bohua Peng, Chenghua Lin, Diana Maynard,
• Abstract summary: This research contributes: (1) A methodology for increasing question difficulty using PPO and synthetic data; (2) Empirical evidence of the method's effectiveness, including human evaluation; and (3) An in-depth error analysis and study of emergent phenomena.
• Score: 11.31451429456241
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As the cultural heritage sector increasingly adopts technologies like Retrieval-Augmented Generation (RAG) to provide more personalised search experiences and enable conversations with collections data, the demand for specialised evaluation datasets has grown. While end-to-end system testing is essential, it's equally important to assess individual components. We target the final, answering task, which is well-suited to Machine Reading Comprehension (MRC). Although existing MRC datasets address general domains, they lack the specificity needed for cultural heritage information. Unfortunately, the manual creation of such datasets is prohibitively expensive for most heritage institutions. This paper presents a cost-effective approach for generating domain-specific MRC datasets with increased difficulty using Reinforcement Learning from Human Feedback (RLHF) from synthetic preference data. Our method leverages the performance of existing question-answering models on a subset of SQuAD to create a difficulty metric, assuming that more challenging questions are answered correctly less frequently. This research contributes: (1) A methodology for increasing question difficulty using PPO and synthetic data; (2) Empirical evidence of the method's effectiveness, including human evaluation; (3) An in-depth error analysis and study of emergent phenomena; and (4) An open-source codebase and set of three llama-2-chat adapters for reproducibility and adaptation.

Related papers

• iTRI-QA: a Toolset for Customized Question-Answer Dataset Generation Using Language Models for Enhanced Scientific Research [1.2411445143550854]
  We present a tool for the development of a customized question-answer (QA) dataset, called Interactive Trained Research Innovator (iTRI) - QA. Our approach integrates curated QA datasets with a specialized research paper dataset to enhance responses' contextual relevance and accuracy using fine-tuned LM. This pipeline provides a dynamic and domain-specific QA system that will be applied for future research LM deployment.
  arXiv  Detail & Related papers  (2025-01-27T23:38:39Z)
• TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data [9.390415313514762]
  TARGA is a framework that generates high-relevance synthetic data without manual annotation. It substantially outperforms existing non-fine-tuned methods that utilize close-sourced model. It exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.
  arXiv  Detail & Related papers  (2024-12-27T09:16:39Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts. With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS) Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements. High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent [102.31558123570437]
  Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs) We propose the first self-adaptive planning agent for multimodal retrieval, OmniSearch.
  arXiv  Detail & Related papers  (2024-11-05T09:27:21Z)
• Synthetic Data Generation with Large Language Models for Personalized Community Question Answering [47.300506002171275]
  We build Sy-SE-PQA based on an existing dataset, SE-PQA, which consists of questions and answers posted on the popular StackExchange communities. Our findings suggest that LLMs have high potential in generating data tailored to users' needs. The synthetic data can replace human-written training data, even if the generated data may contain incorrect information.
  arXiv  Detail & Related papers  (2024-10-29T16:19:08Z)
• Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks [13.829525575305206]
  This paper introduces our Rephrase and Contrast (RaC) framework, an efficient fine-tuning framework. RaC enhances LLMs' comprehension and critical thinking abilities by incorporating question reformulation and contrastive analysis. To efficiently construct the dataset for RaC fine-tuning, we develop a GPT-assisted data mining method for generating high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2024-09-21T16:04:43Z)
• Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models [0.0]
  Open Domain Question Answering (ODQA) within natural language processing involves building systems that answer factual questions using large-scale knowledge corpora. High-quality datasets are used to train models on realistic scenarios. Standardized metrics facilitate comparisons between different ODQA systems.
  arXiv  Detail & Related papers  (2024-06-19T05:43:02Z)
• DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation [83.30006900263744]
  Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights. We propose to automatically generate high-quality answer annotations leveraging the code-generation capabilities of LLMs. Our DACO-RL algorithm is evaluated by human annotators to produce more helpful answers than SFT model in 57.72% cases.
  arXiv  Detail & Related papers  (2024-03-04T22:47:58Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework [51.44863255495668]
  Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence. We present Multi-Modal Reasoning(COCO-MMR) dataset, a novel dataset that encompasses an extensive collection of open-ended questions. We propose innovative techniques, including multi-hop cross-modal attention and sentence-level contrastive learning, to enhance the image and text encoders.
  arXiv  Detail & Related papers  (2023-07-24T08:58:25Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)
• Training Data Augmentation for Deep Learning Radio Frequency Systems [1.1199585259018459]
  This work focuses on the data used during training. In general, the examined data types each have useful contributions to a final application. Despite the benefit of captured data, the difficulties and costs that arise from live collection often make the quantity of data needed to achieve peak performance impractical.
  arXiv  Detail & Related papers  (2020-10-01T02:26:16Z)

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.