Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters, fine-tuning allows the model to learn and update its parameters during a training phase. In this study, we applied fine-tuning to various sized language models using data that contained explanations of the output rather than merely presenting the answers. We found that even smaller language models with as few as 60 million parameters benefited substantially from this approach. Interestingly, our results indicated that the detailed explanations were more beneficial to smaller models than larger ones, with the latter gaining nearly the same advantage from any form of explanation, irrespective of its length. Additionally, we demonstrate that the inclusion of explanations enables the models to solve tasks that they were not able to solve without explanations. Lastly, we argue that despite the challenging nature of adding explanations, samples that contain explanations not only reduce the volume of data required for training but also promote a more effective generalization by the model. In essence, our findings suggest that fine-tuning with explanations significantly bolsters the performance of large language models.
CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation
Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Colorado Anschutz Medical Campus（科罗拉多大学安施图茨医学院）；Loyola University Chicago（芝加哥洛约拉大学）；University of Wisconsin Madison（威斯康星大学麦迪逊分校）
Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples can help LMs. We annotate questions from 40 challenging tasks with answer explanations, and various matched control explanations. We evaluate how different types of explanations, instructions, and controls affect zero- and few-shot performance. We analyze these results using statistical multilevel modeling techniques that account for the nested dependencies…
Chain-of-thought (CoT) prompting enables large language models (LLMs) to solve complex reasoning tasks by generating an explanation before the final prediction. Despite it's promising ability, a critical downside of CoT prompting is that the performance is greatly affected by the factuality of the generated explanation. To improve the correctness of the explanations, fine-tuning language models with explanation data is needed. However, there exists only a few datasets that can be used for such approaches, and no data collection tool for building them. Thus, we introduce CoTEVer, a tool-kit for…
University of Virginia（弗吉尼亚大学）；Microsoft Research（微软研究院）
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from. In this work, we propose to answer this question by interpreting the adaptation behavior using post-hoc explanations from model predictions. By modeling feature statistics of explanations, we discover that (1) without fine-tuning, pre-trained models (e.g. BERT and RoBERTa) show strong prediction bias across labels; (2) although few-shot fine-tuning can mitigate the prediction bias and demonstrate promi…
EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
Technical University of Munich（慕尼黑技术大学）；MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP，信息与语言处理中心，慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））
The University of Manchester（曼彻斯特大学）；CRUK Manchester Institute（英国癌症研究中心曼彻斯特研究所）；Idiap Research Institute（Idiap研究所）
Entailment trees have been proposed to simulate the human reasoning process of explanation generation in the context of open--domain textual question answering. However, in practice, manually constructing these explanation trees proves a laborious process that requires active human involvement. Given the complexity of capturing the line of reasoning from question to the answer or from claim to premises, the issue arises of how to assist the user in efficiently constructing multi--level entailment trees given a large set of available facts. In this paper, we frame the construction of entailment…
Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models
School of Computing, Dublin City University（都柏林城市大学计算机学院）；Iran University of Science and Technology（伊朗科技大学）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；Lucerne School of Computer Science and Information Technology（卢塞恩计算机科学与信息技术学院）
Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；University of Oslo（奥斯陆大学）
This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We develop variants of layer-wise relevance propagation (LRP) and gradient-based explanation methods, tailored to image captioning models with attention mechanisms. We compare the interpretability of attention heatmaps systematically against the explanations provided by explanation methods such as LRP, Grad-CAM, and Guided Grad-CAM. We show that explanation methods provide simultaneously pixel-wise image explanations (supporting and opposing pixels of the input imag…
Johns Hopkins University（约翰霍普金斯大学）；University of Rochester（罗切斯特大学）
Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We demonstrate that gradually fine-tuning in a multi-stage process can yield substantial further gains and can be applied without modifying the model or learning objective.
University of Toronto（多伦多大学）；Microsoft Research（微软研究院）；Beihang University（北京航空航天大学）
Developing models that can automatically generate detailed code explanation can greatly benefit software maintenance and programming education. However, existing code-to-text generation models often produce only high-level summaries of code that do not capture implementation-level choices essential for these scenarios. To fill in this gap, we propose the code explanation generation task. We first conducted a human study to identify the criteria for high-quality explanatory docstring for code. Based on that, we collected and refined a large-scale code docstring corpus and formulated automatic e…
Pre-training a language model and then fine-tuning it for downstream tasks has demonstrated state-of-the-art results for various NLP tasks. Pre-training is usually independent of the downstream task, and previous works have shown that this pre-training alone might not be sufficient to capture the task-specific nuances. We propose a way to tailor a pre-trained BERT model for the downstream task via task-specific masking before the standard supervised fine-tuning. For this, a word list is first collected specific to the task. For example, if the task is sentiment classification, we collect a sma…
Compact Example-Based Explanations for Language Models
Faculty of Computer Science, University of Vienna（维也纳大学计算机科学学院）；UniVie Doctoral School Computer Science, University of Vienna（维也纳大学计算机科学博士学院）；Faculty of Philological and Cultural Studies, University of Vienna（维也纳大学语言文化研究学院）
Enhancing adversarial robustness in Natural Language Inference using explanations
Artificial Intelligence and Learning Systems Laboratory（人工智能与学习系统实验室）；School of Electrical and Computer Engineering（电气与计算机工程学院）；National Technical University of Athens（雅典技术大学）
NLP practitioners often want to take existing trained models and apply them to data from new domains. While fine-tuning or few-shot learning can be used to adapt a base model, there is no single recipe for making these techniques work; moreover, one may not have access to the original model weights if it is deployed as a black box. We study how to improve a black box model's performance on a new domain by leveraging explanations of the model's behavior. Our approach first extracts a set of features combining human intuition about the task with model attributions generated by black box interpre…
