Modern language models capture a large body of factual knowledge. However, some facts can be incorrectly induced or become obsolete over time, resulting in factually incorrect generations. This has led to the development of various editing methods that allow updating facts encoded by the model. Evaluation of these methods has primarily focused on testing whether an individual fact has been successfully injected, and if similar predictions for other subjects have not changed. Here we argue that such evaluation is limited, since injecting one fact (e.g., “Jack Depp is the son of Johnny Depp” ) introduces a “ripple effect” in the form of additional facts that the model needs to update (e.g., “Jack Depp is the sibling of Lily-Rose Depp” ). To address this, we propose novel evaluation criteria that consider the implications of an edit on related facts. Using these criteria, we then construct RippleEdits , a diagnostic benchmark of 5K factual edits, capturing various types of ripple effects. We evaluate prominent editing methods on RippleEdits , showing that they fail to introduce consistent changes in the model’s knowledge. In addition, we find that a simple in-context editing baseline obtains the best scores on our benchmark, suggesting a promising research direction for model editing. 1

Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduce the “Break, Perturb, Build” (BPB) framework for automatic reasoning-oriented perturbation of question-answer pairs. BPB represents a question by decomposing it into the reasoning steps that are required to answer it, symbolically perturbs the decomposition, and then generates new question-answer pairs. We demonstrate the effectiveness of BPB by creating evaluation sets for three reading comprehension (RC) benchmarks, generating thousands of high-quality examples without human intervention. We evaluate a range of RC models on our evaluation sets, which reveals large performance gaps on generated examples compared to the original data. Moreover, symbolic perturbations enable fine-grained analysis of the strengths and limitations of models. Last, augmenting the training data with examples generated by BPB helps close the performance gaps, without any drop on the original data distribution.

A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly . In this work, we introduce S trategy QA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy . A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, S trategy QA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in S trategy QA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of ∼ 66 % .

Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the B reak dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the H otpot QA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use B reak to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines.