LLMs have demonstrated impressive performance in answering medical questions, such as passing scores on medical licensing examinations. However, medical board exam questions or general clinical questions do not capture the complexity of realistic clinical cases. Moreover, the lack of reference explanations means we cannot easily evaluate the reasoning of model decisions, a crucial component of supporting doctors in making complex medical decisions. To address these challenges, we construct two new datasets: JAMA Clinical Challenge and Medbullets. JAMA Clinical Challenge consists of questions based on challenging clinical cases, while Medbullets comprises USMLE Step 2&3 style clinical questions. Both datasets are structured as multiple-choice question-answering tasks, where each question is accompanied by an expert-written explanation. We evaluate four LLMs on the two datasets using various prompts. Experiments demonstrate that our datasets are harder than previous benchmarks. The inconsistency between automatic and human evaluations of model-generated explanations highlights the need to develop new metrics to support future research on explainable medical QA.
Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive ground truth, their evaluation remains a challenge. Existing evaluation metrics rely on the degree to which a rationale supports a target label, but we find these fall short in evaluating rationales that inadvertently leak the labels. To address this problem, we propose RORA, a Robust free-text Rationale evaluation against label leakage. RORA quantifies the new information supplied by a rationale to justify the label. This is achieved by assessing the conditional V-information \citep{hewitt-etal-2021-conditional} with a predictive family robust against leaky features that can be exploited by a small model. RORA consistently outperforms existing approaches in evaluating human-written, synthetic, or model-generated rationales, particularly demonstrating robustness against label leakage. We also show that RORA aligns well with human judgment, providing a more reliable and accurate measurement across diverse free-text rationales.
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this paper, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations, and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional machine learning models.
Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative words using the learned word interactions. Our layer, we call WIGRAPH, can plug into any neural network-based NLP text classifiers right after its word embedding layer. Across multiple SOTA NLP models and various NLP datasets, we demonstrate that adding the WIGRAPH layer substantially improves NLP models' interpretability and enhances models' prediction performance at the same time.
Free-text rationales (FTRs) follow how humans communicate by explaining reasoning processes via natural language. A number of recent works have studied how to improve language model (LM) generalization by using FTRs to teach LMs the correct reasoning processes behind correct task outputs. These prior works aim to learn from FTRs by appending them to the LM input or target output, but this may introduce an input distribution shift or conflict with the task objective, respectively. We propose KNIFE, which distills FTR knowledge from an FTR-augmented teacher LM (takes both task input and FTR) to a student LM (takes only task input), which is used for inference. Crucially, the teacher LM's forward computation has a bottleneck stage in which all of its FTR states are masked out, which pushes knowledge from the FTR states into the task input/output states. Then, FTR knowledge is distilled to the student LM by training its task input/output states to align with the teacher LM's. On two question answering datasets, we show that KNIFE significantly outperforms existing FTR learning methods, in both fully-supervised and low-resource settings.
Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model. This raises the interest and concern in the stability of post-hoc explanations. However, the remaining question is: is the instability caused by the neural network model or the post-hoc explanation method? This work explores the potential source that leads to unstable post-hoc explanations. To separate the influence from the model, we propose a simple output probability perturbation method. Compared to prior input side perturbation methods, the output probability perturbation method can circumvent the neural model's potential effect on the explanations and allow the analysis on the explanation method. We evaluate the proposed method with three widely-used post-hoc explanation methods (LIME (Ribeiro et al., 2016), Kernel Shapley (Lundberg and Lee, 2017a), and Sample Shapley (Strumbelj and Kononenko, 2010)). The results demonstrate that the post-hoc methods are stable, barely producing discrepant explanations under output probability perturbations. The observation suggests that neural network models may be the primary source of fragile explanations.
Free-text rationales are a promising step towards explainable AI, yet their evaluation remains an open research problem. While existing metrics have mostly focused on measuring the direct association between the rationale and a given label, we argue that an ideal metric should also be able to focus on the new information uniquely provided in the rationale that is otherwise not provided in the input or the label. We investigate this research problem from an information-theoretic perspective using the conditional V-information. More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), that can quantify the new information in a rationale supporting a given label beyond the information already available in the input or the label. Experiments on reasoning tasks across four benchmarks, including few-shot prompting with GPT-3, demonstrate the effectiveness of REV in evaluating different types of rationale-label pairs, compared to existing metrics. Through several quantitative comparisons, we demonstrate the capability of REV in providing more sensitive measurements of new information in free-text rationales with respect to a label. Furthermore, REV is consistent with human judgments on rationale evaluations. Overall, when used alongside traditional performance metrics, REV provides deeper insights into a models' reasoning and prediction processes.