Evaluating the trustworthiness of a model's prediction is essential for differentiating between `right for the right reasons' and `right for the wrong reasons'. Identifying textual spans that determine the target label, known as faithful rationales, usually relies on pipeline approaches or reinforcement learning. However, such methods either require supervision and thus costly annotation of the rationales or employ non-differentiable models. We propose a differentiable training-framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task. To achieve this, our model solves the task based on each rationale individually and learns to assign high scores to those which solved the task best. Our evaluation on three different datasets shows competitive results compared to a standard BERT blackbox while exceeding a pipeline counterpart's performance in two cases. We further exploit the transparent decision-making process of these models to prefer selecting the correct rationales by applying direct supervision, thereby boosting the performance on the rationale-level.
Georgia Institute of Technology（佐治亚理工学院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. While prior work focuses on extractive rationales (a subset of the input words), we investigate their less-studied counterpart: free-text natural language rationales. We demonstrate that pipelines, existing models for faithful extractive rationalization on information-extraction style tasks, do not extend as reliably to "reasoning" tasks requiring free-text rationales. We turn to models that jointly predict and rationalize, a class of widely used high-performance mod…
While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target. To tackle this problem, we experimented with a state-of-the-art relation extraction model. Surprisingly, we found that despite reasonable performance, the model's attention was often systematically misaligned with the words that contribute to sentiment. Thus, we directly trained the model's attention with human rationales and improved our model performance by a robust 4~8 points on all tasks we defined on our data sets. We…
The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other …
Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies
Computational Linguistics and Text Mining Lab, Vrije Universiteit Amsterdam（范德比尔特大学阿姆斯特丹计算语言学与文本挖掘实验室）；Institute of Computer Science, University of Göttingen（哥廷根大学计算机科学学院）
MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；UMass Amherst（马萨诸塞大学阿默斯特分校）；Tsinghua University（清华大学）
Large pre-trained vision and language models have demonstrated remarkable capacities for various tasks. However, solving the knowledge-based visual reasoning tasks remains challenging, which requires a model to comprehensively understand image content, connect the external world knowledge, and perform step-by-step reasoning to answer the questions correctly. To this end, we propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. The see stage scans the image and grounds the v…
Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work, we re-purpose a sentence editing dataset, where faithful high-quality human rationales can be automatically extracted and compared with extracted model rationales, as a new testbed for interpretability. This enables us to conduct a systematic investigation on an array of questions regarding PLMs' interpretability, including the role of pre-training procedure,…
Self-Explaining Hate Speech Detection with Moral Rationales
University of São Paulo（圣保罗大学）；University of Southern California（南加州大学）；Saarland University（萨尔兰大学）；Virginia Tech（弗吉尼亚理工大学）；University of Melbourne（墨尔本大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Technical University of Munich（慕尼黑技术大学）；Google Research（谷歌研究）；Portland State University（波特兰州立大学）
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
School of Informatics, Xiamen University（厦门大学信息学院）；Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）；The Hong Kong Polytechnic University（香港理工大学）；Migu Meland Co., Ltd（Migu Meland公司）；Soochow University（苏州大学）；Singapore Management University（新加坡管理大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
IDEA Research, International Digital Economy Academy（国际数字经济学院IDEA研究院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；The Chinese University of Hong Kong（香港中文大学）；The Hong Kong University of Science and Technology（香港科技大学）
