Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering

• URL: http://arxiv.org/abs/2402.08277v5
• Date: Mon, 3 Jun 2024 16:48:59 GMT
• Title: Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
• Authors: Tobias Schimanski, Jingwei Ni, Mathias Kraus, Elliott Ash, Markus Leippold,
• Abstract summary: We investigate how to robustly fine-tune Large Language Models (LLMs) for better source quality and answer attributability. Specifically, we introduce a data generation pipeline with automated data quality filters, which can synthesize diversified high-quality training and testing data at scale. Extensive evaluation shows that fine-tuning on synthetic data improves performance on both in- and out-of-distribution.
• Score: 10.624293689624151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is basing the answers on reliable sources. However, this Evidence-Based QA has proven to work insufficiently with LLMs in terms of citing the correct sources (source quality) and truthfully representing the information within sources (answer attributability). In this work, we systematically investigate how to robustly fine-tune LLMs for better source quality and answer attributability. Specifically, we introduce a data generation pipeline with automated data quality filters, which can synthesize diversified high-quality training and testing data at scale. We further introduce four test sets to benchmark the robustness of fine-tuned specialist models. Extensive evaluation shows that fine-tuning on synthetic data improves performance on both in- and out-of-distribution. Furthermore, we show that data quality, which can be drastically improved by proposed quality filters, matters more than quantity in improving Evidence-Based QA.

Related papers

• How Reliable Is Human Feedback For Aligning Large Language Models? [24.66495636695214]
  We conduct a comprehensive study and provide an in-depth analysis of human feedback data. We identify six key sources of unreliability, such as mis-labeling, subjective preferences, differing criteria and thresholds for helpfulness and harmlessness. We propose Source-Aware Cleaning, an automatic data-cleaning method guided by the insight of our qualitative analysis, to significantly improve data quality.
  arXiv  Detail & Related papers  (2024-10-02T19:03:42Z)
• Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation [19.312330150540912]
  An emerging application is using Large Language Models (LLMs) to enhance retrieval-augmented generation (RAG) capabilities. We propose FRAMES, a high-quality evaluation dataset designed to test LLMs' ability to provide factual responses. We present baseline results demonstrating that even state-of-the-art LLMs struggle with this task, achieving 0.40 accuracy with no retrieval.
  arXiv  Detail & Related papers  (2024-09-19T17:52:07Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement. We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent. Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• Improving Retrieval Augmented Language Model with Self-Reasoning [20.715106330314605]
  We propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs. The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process. We have evaluated our framework across four public datasets to demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2024-07-29T09:05:10Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Enhancing Data Quality in Federated Fine-Tuning of Foundation Models [54.757324343062734]
  We propose a data quality control pipeline for federated fine-tuning of foundation models. This pipeline computes scores reflecting the quality of training data and determines a global threshold for a unified standard. Our experiments show that the proposed quality control pipeline facilitates the effectiveness and reliability of the model training, leading to better performance.
  arXiv  Detail & Related papers  (2024-03-07T14:28:04Z)
• How to Train Data-Efficient LLMs [56.41105687693619]
  We study data-efficient approaches for pre-training language models (LLMs) We find that Ask-LLM and Density sampling are the best methods in their respective categories. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories.
  arXiv  Detail & Related papers  (2024-02-15T02:27:57Z)
• Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately [2.1715455600756646]
  Large Language Models (LLMs) generate responses to questions. Their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models.
  arXiv  Detail & Related papers  (2024-01-27T00:18:07Z)
• QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation [67.27999343730224]
  We introduce an iterative bootstrapping framework for QA data augmentation (named QASnowball) QASnowball can iteratively generate large-scale high-quality QA data based on a seed set of supervised examples. We conduct experiments in the high-resource English scenario and the medium-resource Chinese scenario, and the experimental results show that the data generated by QASnowball can facilitate QA models.
  arXiv  Detail & Related papers  (2023-09-19T05:20:36Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)

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.