Oana-Maria Camburu

Zhongbin Xie, Vid Kocijan, Thomas Lukasiewicz et al. · oxford

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where previous datasets are either hand-crafted or fail to reliably measure an explicitly defined bias. To overcome these shortcomings, we propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation, and construct Counter-GAP, an annotated dataset consisting of 4008 instances grouped into 1002 quadruples. We further identify a bias cancellation problem in previous group-level metrics on Counter-GAP, and propose to use the difference between inconsistency across genders and within genders to measure bias at a quadruple level. Our results show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group, and that a name-based counterfactual data augmentation method is more effective to mitigate such bias than an anonymization-based method.

Maxime Kayser, Cornelius Emde, Oana-Maria Camburu et al.

Most deep learning algorithms lack explanations for their predictions, which limits their deployment in clinical practice. Approaches to improve explainability, especially in medical imaging, have often been shown to convey limited information, be overly reassuring, or lack robustness. In this work, we introduce the task of generating natural language explanations (NLEs) to justify predictions made on medical images. NLEs are human-friendly and comprehensive, and enable the training of intrinsically explainable models. To this goal, we introduce MIMIC-NLE, the first, large-scale, medical imaging dataset with NLEs. It contains over 38,000 NLEs, which explain the presence of various thoracic pathologies and chest X-ray findings. We propose a general approach to solve the task and evaluate several architectures on this dataset, including via clinician assessment.

Myeongjun Jang, Bodhisattwa Prasad Majumder, Julian McAuley et al.

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.

Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that lead the model to give its prediction on that instance. For example, the subphrase ``he stole the mobile phone'' can be an extractive rationale for the prediction of ``Theft''. Previous works on generating extractive rationales usually employ a two-phase model: a selector that selects the most important features (i.e., the rationale) followed by a predictor that makes the prediction based exclusively on the selected features. One disadvantage of these works is that the main signal for learning to select features comes from the comparison of the answers given by the predictor to the ground-truth answers. In this work, we propose to squeeze more information from the predictor via an information calibration method. More precisely, we train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. The first model is used as a guide for the second model. We use an adversarial technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features. In addition, for natural language tasks, we propose a language-model-based regularizer to encourage the extraction of fluent rationales. Experimental results on a sentiment analysis task, a hate speech recognition task as well as on three tasks from the legal domain show the effectiveness of our approach to rationale extraction.

Xuanli He, Yuxiang Wu, Oana-Maria Camburu et al. · oxford

Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL). However, recent works show that ICL-prompted models tend to produce inaccurate results when presented with adversarial inputs. In this work, we investigate whether augmenting ICL with natural language explanations (NLEs) improves the robustness of LLMs on adversarial datasets covering natural language inference and paraphrasing identification. We prompt LLMs with a small set of human-generated NLEs to produce further NLEs, yielding more accurate results than both a zero-shot-ICL setting and using only human-generated NLEs. Our results on five popular LLMs (GPT3.5-turbo, Llama2, Vicuna, Zephyr, and Mistral) show that our approach yields over 6% improvement over baseline approaches for eight adversarial datasets: HANS, ISCS, NaN, ST, PICD, PISP, ANLI, and PAWS. Furthermore, previous studies have demonstrated that prompt selection strategies significantly enhance ICL on in-distribution test sets. However, our findings reveal that these strategies do not match the efficacy of our approach for robustness evaluations, resulting in an accuracy drop of 8% compared to the proposed approach.

David Chanin, Anthony Hunter, Oana-Maria Camburu

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a technique called linear relational concepts (LRC) for finding concept directions corresponding to human-interpretable concepts by first modeling the relation between subject and object as a linear relational embedding (LRE). We find that inverting the LRE and using earlier object layers results in a powerful technique for finding concept directions that outperforms standard black-box probing classifiers. We evaluate LRCs on their performance as concept classifiers as well as their ability to causally change model output.

Iván Arcuschin, David Chanin, Adrià Garriga-Alonso et al.

Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these *unverbalized biases*. Monitoring models via their stated reasoning is therefore unreliable, and existing bias evaluations typically require predefined categories and hand-crafted datasets. In this work, we introduce a fully automated, black-box pipeline for detecting task-specific unverbalized biases. Given a task dataset, the pipeline uses LLM autoraters to generate candidate bias concepts. It then tests each concept on progressively larger input samples by generating positive and negative variations, and applies statistical techniques for multiple testing and early stopping. A concept is flagged as an unverbalized bias if it yields statistically significant performance differences while not being cited as justification in the model's CoTs. We evaluate our pipeline across six LLMs on three decision tasks (hiring, loan approval, and university admissions). Our technique automatically discovers previously unknown biases in these models (e.g., Spanish fluency, English proficiency, writing formality). In the same run, the pipeline also validates biases that were manually identified by prior work (gender, race, religion, ethnicity). More broadly, our proposed approach provides a practical, scalable path to automatic task-specific bias discovery.

Vinitra Swamy, Davide Romano, Bhargav Srinivasa Desikan et al.

Recent advances in eXplainable AI (XAI) for education have highlighted a critical challenge: ensuring that explanations for state-of-the-art AI models are understandable for non-technical users such as educators and students. In response, we introduce iLLuMinaTE, a zero-shot, chain-of-prompts LLM-XAI pipeline inspired by Miller's cognitive model of explanation. iLLuMinaTE is designed to deliver theory-driven, actionable feedback to students in online courses. iLLuMinaTE navigates three main stages - causal connection, explanation selection, and explanation presentation - with variations drawing from eight social science theories (e.g. Abnormal Conditions, Pearl's Model of Explanation, Necessity and Robustness Selection, Contrastive Explanation). We extensively evaluate 21,915 natural language explanations of iLLuMinaTE extracted from three LLMs (GPT-4o, Gemma2-9B, Llama3-70B), with three different underlying XAI methods (LIME, Counterfactuals, MC-LIME), across students from three diverse online courses. Our evaluation involves analyses of explanation alignment to the social science theory, understandability of the explanation, and a real-world user preference study with 114 university students containing a novel actionability simulation. We find that students prefer iLLuMinaTE explanations over traditional explainers 89.52% of the time. Our work provides a robust, ready-to-use framework for effectively communicating hybrid XAI-driven insights in education, with significant generalization potential for other human-centric fields.

Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz et al.

When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors actually responsible for the decision? In this work, we analyse counterfactual faithfulness across 75 models from 13 families. We analyze the tradeoff between conciseness and comprehensiveness, how correlational faithfulness metrics assess this tradeoff, and the extent to which metrics can be gamed. This analysis motivates two new metrics: the phi-CCT, a simplified variant of the Correlational Counterfactual Test (CCT) which avoids the need for token probabilities while explaining most of the variance of the original test; and F-AUROC, which eliminates sensitivity to imbalanced intervention distributions and captures a model's ability to produce explanations with different levels of detail. Our findings reveal a clear scaling trend: larger and more capable models are consistently more faithful on all metrics we consider. Our code is available at https://github.com/google-deepmind/corr_faith.

Magnus Sesodia, Alina Petrova, John Armour et al.

Legal systems worldwide continue to struggle with overwhelming caseloads, limited judicial resources, and growing complexities in legal proceedings. Artificial intelligence (AI) offers a promising solution, with Legal Judgment Prediction (LJP) -- the practice of predicting a court's decision from the case facts -- emerging as a key research area. However, existing datasets often formulate the task of LJP unrealistically, not reflecting its true difficulty. They also lack high-quality annotation essential for legal reasoning and explainability. To address these shortcomings, we introduce AnnoCaseLaw, a first-of-its-kind dataset of 471 meticulously annotated U.S. Appeals Court negligence cases. Each case is enriched with comprehensive, expert-labeled annotations that highlight key components of judicial decision making, along with relevant legal concepts. Our dataset lays the groundwork for more human-aligned, explainable LJP models. We define three legally relevant tasks: (1) judgment prediction; (2) concept identification; and (3) automated case annotation, and establish a performance baseline using industry-leading large language models (LLMs). Our results demonstrate that LJP remains a formidable task, with application of legal precedent proving particularly difficult. Code and data are available at https://github.com/anonymouspolar1/annocaselaw.

Maxime Kayser, Oana-Maria Camburu, Leonard Salewski et al.

Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, there is a lack of comparison between existing methods, which is due to a lack of re-usable evaluation frameworks and a scarcity of datasets. In this work, we introduce e-ViL and e-SNLI-VE. e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs (over 430k instances). We also propose a new model that combines UNITER, which learns joint embeddings of images and text, and GPT-2, a pre-trained language model that is well-suited for text generation. It surpasses the previous state of the art by a large margin across all datasets. Code and data are available here: https://github.com/maximek3/e-ViL.

Noah Y. Siegel, Oana-Maria Camburu, Nicolas Heess et al.

In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces that sound plausible and receive high ratings from human annotators. However, it is unclear to what extent these explanations are faithful, i.e., truly capture the factors responsible for the model's predictions. In this work, we introduce Correlational Explanatory Faithfulness (CEF), a metric that can be used in faithfulness tests based on input interventions. Previous metrics used in such tests take into account only binary changes in the predictions. Our metric accounts for the total shift in the model's predicted label distribution, more accurately reflecting the explanations' faithfulness. We then introduce the Correlational Counterfactual Test (CCT) by instantiating CEF on the Counterfactual Test (CT) from Atanasova et al. (2023). We evaluate the faithfulness of free-text explanations generated by few-shot-prompted LLMs from the Llama2 family on three NLP tasks. We find that our metric measures aspects of faithfulness which the CT misses.

Maxime Kayser, Bayar Menzat, Cornelius Emde et al.

The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making their inference process more transparent. However, current explainability methods are seldom evaluated in the way they are intended to be used: by real-world end users. To address this, we conducted a large-scale user study with 85 healthcare practitioners in the context of human-AI collaborative chest X-ray analysis. We evaluated three types of explanations: visual explanations (saliency maps), natural language explanations, and a combination of both modalities. We specifically examined how different explanation types influence users depending on whether the AI advice and explanations are factually correct. We find that text-based explanations lead to significant over-reliance, which is alleviated by combining them with saliency maps. We also observe that the quality of explanations, that is, how much factually correct information they entail, and how much this aligns with AI correctness, significantly impacts the usefulness of the different explanation types.

Pepa Atanasova, Oana-Maria Camburu, Christina Lioma et al.

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to present reasons that are unfaithful to the model's inner workings. This work explores the challenging question of evaluating the faithfulness of natural language explanations (NLEs). To this end, we present two tests. First, we propose a counterfactual input editor for inserting reasons that lead to counterfactual predictions but are not reflected by the NLEs. Second, we reconstruct inputs from the reasons stated in the generated NLEs and check how often they lead to the same predictions. Our tests can evaluate emerging NLE models, proving a fundamental tool in the development of faithful NLEs.

Jesus Solano, Mardhiyah Sanni, Oana-Maria Camburu et al.

Models that generate natural language explanations (NLEs) for their predictions have recently gained increasing interest. However, this approach usually demands large datasets of human-written NLEs for the ground-truth answers at training time, which can be expensive and potentially infeasible for some applications. When only a few NLEs are available (a few-shot setup), fine-tuning pre-trained language models (PLMs) in conjunction with prompt-based learning has recently shown promising results. However, PLMs typically have billions of parameters, making full fine-tuning expensive. We propose SparseFit, a sparse few-shot fine-tuning strategy that leverages discrete prompts to jointly generate predictions and NLEs. We experiment with SparseFit on three sizes of the T5 language model and four datasets and compare it against existing state-of-the-art Parameter-Efficient Fine-Tuning (PEFT) techniques. We find that fine-tuning only 6.8% of the model parameters leads to competitive results for both the task performance and the quality of the generated NLEs compared to full fine-tuning of the model and produces better results on average than other PEFT methods in terms of predictive accuracy and NLE quality.

Joe Stacey, Pasquale Minervini, Haim Dubossarsky et al.

With recent advances, neural models can achieve human-level performance on various natural language tasks. However, there are no guarantees that any explanations from these models are faithful, i.e. that they reflect the inner workings of the model. Atomic inference overcomes this issue, providing interpretable and faithful model decisions. This approach involves making predictions for different components (or atoms) of an instance, before using interpretable and deterministic rules to derive the overall prediction based on the individual atom-level predictions. We investigate the effectiveness of using LLM-generated facts as atoms, decomposing Natural Language Inference premises into lists of facts. While directly using generated facts in atomic inference systems can result in worse performance, with 1) a multi-stage fact generation process, and 2) a training regime that incorporates the facts, our fact-based method outperforms other approaches.

Yordan Yordanov, Vid Kocijan, Thomas Lukasiewicz et al.

Training a model to provide natural language explanations (NLEs) for its predictions usually requires the acquisition of task-specific NLEs, which is time- and resource-consuming. A potential solution is the few-shot out-of-domain transfer of NLEs from a parent task with many NLEs to a child task. In this work, we examine the setup in which the child task has few NLEs but abundant labels. We establish four few-shot transfer learning methods that cover the possible fine-tuning combinations of the labels and NLEs for the parent and child tasks. We transfer explainability from a large natural language inference dataset (e-SNLI) separately to two child tasks: (1) hard cases of pronoun resolution, where we introduce the small-e-WinoGrande dataset of NLEs on top of the WinoGrande dataset, and (2)~commonsense validation (ComVE). Our results demonstrate that the parent task helps with NLE generation and we establish the best methods for this setup.

Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz et al.

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing RExC, a self-rationalizing framework that grounds its predictions and two complementary types of explanations (NLEs and extractive rationales) in background knowledge. Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations. Furthermore, a perturbation analysis in RExC shows a high degree of association between explanations and predictions, a necessary property of faithful explanations.

Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that lead the model to give its prediction on the instance. Previous works on generating extractive rationales usually employ a two-phase model: a selector that selects the most important features (i.e., the rationale) followed by a predictor that makes the prediction based exclusively on the selected features. One disadvantage of these works is that the main signal for learning to select features comes from the comparison of the answers given by the predictor and the ground-truth answers. In this work, we propose to squeeze more information from the predictor via an information calibration method. More precisely, we train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. The first model is used as a guide to the second model. We use an adversarial-based technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features. In addition, for natural language tasks, we propose to use a language-model-based regularizer to encourage the extraction of fluent rationales. Experimental results on a sentiment analysis task as well as on three tasks from the legal domain show the effectiveness of our approach to rationale extraction.

Vid Kocijan, Oana-Maria Camburu, Thomas Lukasiewicz

Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing. However, undesired patterns in the collected data can make such tests incorrect. For example, if the feminine subset of a gender-bias-measuring coreference resolution dataset contains sentences with a longer average distance between the pronoun and the correct candidate, an RNN-based model may perform worse on this subset due to long-term dependencies. In this work, we introduce a theoretically grounded method for weighting test samples to cope with such patterns in the test data. We demonstrate the method on the GAP dataset for coreference resolution. We annotate GAP with spans of all personal names and show that examples in the female subset contain more personal names and a longer distance between pronouns and their referents, potentially affecting the bias score in an undesired way. Using our weighting method, we find the set of weights on the test instances that should be used for coping with these correlations, and we re-evaluate 16 recently released coreference models.

Yordan Yordanov, Oana-Maria Camburu, Vid Kocijan et al.

Hard cases of pronoun resolution have been used as a long-standing benchmark for commonsense reasoning. In the recent literature, pre-trained language models have been used to obtain state-of-the-art results on pronoun resolution. Overall, four categories of training and evaluation objectives have been introduced. The variety of training datasets and pre-trained language models used in these works makes it unclear whether the choice of training objective is critical. In this work, we make a fair comparison of the performance and seed-wise stability of four models that represent the four categories of objectives. Our experiments show that the objective of sequence ranking performs the best in-domain, while the objective of semantic similarity between candidates and pronoun performs the best out-of-domain. We also observe a seed-wise instability of the model using sequence ranking, which is not the case when the other objectives are used.

Oana-Maria Camburu

Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users. In various domains, such as healthcare, finance, or law, it is critical to know the reasons behind a decision made by an artificial intelligence system. Therefore, several directions for explaining neural models have recently been explored. In this thesis, I investigate two major directions for explaining deep neural networks. The first direction consists of feature-based post-hoc explanatory methods, that is, methods that aim to explain an already trained and fixed model (post-hoc), and that provide explanations in terms of input features, such as tokens for text and superpixels for images (feature-based). The second direction consists of self-explanatory neural models that generate natural language explanations, that is, models that have a built-in module that generates explanations for the predictions of the model.

Oana-Maria Camburu, Eleonora Giunchiglia, Jakob Foerster et al.

For neural models to garner widespread public trust and ensure fairness, we must have human-intelligible explanations for their predictions. Recently, an increasing number of works focus on explaining the predictions of neural models in terms of the relevance of the input features. In this work, we show that feature-based explanations pose problems even for explaining trivial models. We show that, in certain cases, there exist at least two ground-truth feature-based explanations, and that, sometimes, neither of them is enough to provide a complete view of the decision-making process of the model. Moreover, we show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations, despite the apparently implicit assumption that explainers should look for one specific feature-based explanation. These findings bring an additional dimension to consider in both developing and choosing explainers.

Virginie Do, Oana-Maria Camburu, Zeynep Akata et al.

The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning. However, the automatic way in which SNLI-VE has been assembled (via combining parts of two related datasets) gives rise to a large number of errors in the labels of this corpus. In this paper, we first present a data collection effort to correct the class with the highest error rate in SNLI-VE. Secondly, we re-evaluate an existing model on the corrected corpus, which we call SNLI-VE-2.0, and provide a quantitative comparison with its performance on the non-corrected corpus. Thirdly, we introduce e-SNLI-VE, which appends human-written natural language explanations to SNLI-VE-2.0. Finally, we train models that learn from these explanations at training time, and output such explanations at testing time.

Oana-Maria Camburu, Brendan Shillingford, Pasquale Minervini et al.

To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show that such models are nonetheless prone to generating mutually inconsistent explanations, such as "Because there is a dog in the image" and "Because there is no dog in the [same] image", exposing flaws in either the decision-making process of the model or in the generation of the explanations. We introduce a simple yet effective adversarial framework for sanity checking models against the generation of inconsistent natural language explanations. Moreover, as part of the framework, we address the problem of adversarial attacks with full target sequences, a scenario that was not previously addressed in sequence-to-sequence attacks. Finally, we apply our framework on a state-of-the-art neural natural language inference model that provides natural language explanations for its predictions. Our framework shows that this model is capable of generating a significant number of inconsistent explanations.

Oana-Maria Camburu, Eleonora Giunchiglia, Jakob Foerster et al.

For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we identify two issues of current explanatory methods. First, we show that two prevalent perspectives on explanations --- feature-additivity and feature-selection --- lead to fundamentally different instance-wise explanations. In the literature, explainers from different perspectives are currently being directly compared, despite their distinct explanation goals. The second issue is that current post-hoc explainers are either validated under simplistic scenarios (on simple models such as linear regression, or on models trained on syntactic datasets), or, when applied to real-world neural networks, explainers are commonly validated under the assumption that the learned models behave reasonably. However, neural networks often rely on unreasonable correlations, even when producing correct decisions. We introduce a verification framework for explanatory methods under the feature-selection perspective. Our framework is based on a non-trivial neural network architecture trained on a real-world task, and for which we are able to provide guarantees on its inner workings. We validate the efficacy of our evaluation by showing the failure modes of current explainers. We aim for this framework to provide a publicly available, off-the-shelf evaluation when the feature-selection perspective on explanations is needed.

Vid Kocijan, Oana-Maria Camburu, Ana-Maria Cretu et al.

Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datasets, such as GAP, DPR, WNLI, PDP, WinoBias, and WinoGender. We release our model to be used off-the-shelf for solving pronoun disambiguation.

Vid Kocijan, Ana-Maria Cretu, Oana-Maria Camburu et al.

The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 strongly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5% and 74.7% on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.8% and 9.6%, respectively. Furthermore, our fine-tuned models are also consistently more robust on the "complex" subsets of WSC273, introduced by Trichelair et al. (2018).

Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz et al.

In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time. In this work, we extend the Stanford Natural Language Inference dataset with an additional layer of human-annotated natural language explanations of the entailment relations. We further implement models that incorporate these explanations into their training process and output them at test time. We show how our corpus of explanations, which we call e-SNLI, can be used for various goals, such as obtaining full sentence justifications of a model's decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets. Our dataset thus opens up a range of research directions for using natural language explanations, both for improving models and for asserting their trust.