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.

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.

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.

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.

Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL). However, recentworks 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.

In order to oversee advanced AI systems, it is important to understand their reasons for generating a given output. 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 truly capturing the factors responsible for the model’s predictions: the most “human-like” explanation may be different from the one that is most faithful to the model’s true decision making process. In this work, we introduce the correlational counterfactual test (CCT), a faithfulness metric based on counterfactual input edits that takes into account not just the binary label change, but the total shift in the model’s predicted label distribution. We evaluate the faithfulness of free-text explanations generated by few-shot-prompted LLMs from the Llama-2 family on three NLP tasks. We find that these explanations are indeed more likely to mention factors when they are impactful to the model’s prediction, with the degree of association increasing with model size but varying significantly by task.

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.

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.

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.

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.

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.

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.

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 consistently and robustly 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 accurate on the “complex” subsets of WSC273, introduced by Trichelair et al. (2018).

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.