The rise of the term "mechanistic interpretability" has accompanied increasing interest in understanding neural models -- particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean to be "mechanistic"? We describe four uses of the term in interpretability research. The most narrow technical definition requires a claim of causality, while a broader technical definition allows for any exploration of a model's internals. However, the term also has a narrow cultural definition describing a cultural movement. To understand this semantic drift, we present a history of the NLP interpretability community and the formation of the separate, parallel "mechanistic" interpretability community. Finally, we discuss the broad cultural definition -- encompassing the entire field of interpretability -- and why the traditional NLP interpretability community has come to embrace it. We argue that the polysemy of "mechanistic" is the product of a critical divide within the interpretability community.

Questions involving commonsense reasoning about everyday situations often admit many $\textit{possible}$ or $\textit{plausible}$ answers. In contrast, multiple-choice question (MCQ) benchmarks for commonsense reasoning require a hard selection of a single correct answer, which, in principle, should represent the $\textit{most}$ plausible answer choice. On $250$ MCQ items sampled from two commonsense reasoning benchmarks, we collect $5,000$ independent plausibility judgments on answer choices. We find that for over 20% of the sampled MCQs, the answer choice rated most plausible does not match the benchmark gold answers; upon manual inspection, we confirm that this subset exhibits higher rates of problems like ambiguity or semantic mismatch between question and answer choices. Experiments with LLMs reveal low accuracy and high variation in performance on the subset, suggesting our plausibility criterion may be helpful in identifying more reliable benchmark items for commonsense evaluation.

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this taxonomy to develop a new evaluation suite of 1000 noncompliance prompts. We find that most existing models show significantly high compliance rates in certain previously understudied categories with models like GPT-4 incorrectly complying with as many as 30% of requests. To address these gaps, we explore different training strategies using a synthetically-generated training set of requests and expected noncompliant responses. Our experiments demonstrate that while direct finetuning of instruction-tuned models can lead to both over-refusal and a decline in general capabilities, using parameter efficient methods like low rank adapters helps to strike a good balance between appropriate noncompliance and other capabilities.

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language models have continually improved. In this paper, we present the surprising conclusion that current language models often generalize relatively well from easy to hard data, even performing as well as "oracle" models trained on hard data. We demonstrate this kind of easy-to-hard generalization using simple training methods like in-context learning, linear classifier heads, and QLoRA for seven different measures of datapoint hardness, including six empirically diverse human hardness measures (like grade level) and one model-based measure (loss-based). Furthermore, we show that even if one cares most about model performance on hard data, it can be better to collect and train on easy data rather than hard data, since hard data is generally noisier and costlier to collect. Our experiments use open models up to 70b in size and four publicly available question-answering datasets with questions ranging in difficulty from 3rd grade science questions to college level STEM questions and general-knowledge trivia. We conclude that easy-to-hard generalization in LMs is surprisingly strong for the tasks studied, suggesting the scalable oversight problem may be easier than previously thought. Our code is available at https://github.com/allenai/easy-to-hard-generalization

Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generating narratives over time, and critically lack basic commonsense reasoning. Furthermore, existing methods generally focus only on single-character stories, or fail to track characters at all. To improve the coherence of generated narratives and to expand the scope of character-centric narrative generation, we introduce Commonsense-inference Augmented neural StoryTelling (CAST), a framework for introducing commonsense reasoning into the generation process with the option to model the interaction between multiple characters. We find that our CAST method produces significantly more coherent, on-topic, enjoyable and fluent stories than existing models in both the single-character and two-character settings in three storytelling domains.

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e.g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance. Are these correlations picked up by models trained on the full input data? To address this question, we propose a new evaluation method, Counterfactual Attentiveness Test (CAT). CAT uses counterfactuals by replacing part of the input with its counterpart from a different example (subject to some restrictions), expecting an attentive model to change its prediction. Using CAT, we systematically investigate established supervised and in-context learning models on ten datasets spanning four tasks: natural language inference, reading comprehension, paraphrase detection, and visual & language reasoning. CAT reveals that reliance on such correlations is mainly data-dependent. Surprisingly, we find that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves. Our results demonstrate that augmenting training or demonstration data with counterfactuals is effective in improving models' attentiveness. We show that models' attentiveness measured by CAT reveals different conclusions from solely measuring correlations in data.

Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training (Meng et al., 2023). However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer. Commonsense knowledge with multiple correct answers, e.g., an apple can be green or red but not transparent, has not been studied but is as essential for enhancing transformers' reliability and usefulness. In this paper, we investigate whether commonsense judgments are causally associated with localized, editable parameters in Transformers, and we provide an affirmative answer. We find that directly applying the MEMIT editing algorithm results in sub-par performance and improve it for the commonsense domain by varying edit tokens and improving the layer selection strategy, i.e., $MEMIT_{CSK}$. GPT-2 Large and XL models edited using $MEMIT_{CSK}$ outperform best-fine-tuned baselines by 10.97% and 10.73% F1 scores on PEP3k and 20Q datasets. In addition, we propose a novel evaluation dataset, PROBE SET, that contains unaffected and affected neighborhoods, affected paraphrases, and affected reasoning challenges. $MEMIT_{CSK}$ performs well across the metrics while fine-tuning baselines show significant trade-offs between unaffected and affected metrics. These results suggest a compelling future direction for incorporating feedback about common sense into Transformers through direct model editing.

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and feedback provider. We evaluate Self-Refine across 7 diverse tasks, ranging from dialog response generation to mathematical reasoning, using state-of-the-art (GPT-3.5, ChatGPT, and GPT-4) LLMs. Across all evaluated tasks, outputs generated with Self-Refine are preferred by humans and automatic metrics over those generated with the same LLM using conventional one-step generation, improving by ~20% absolute on average in task performance. Our work demonstrates that even state-of-the-art LLMs like GPT-4 can be further improved at test time using our simple, standalone approach.

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as a loss signal to train models to produce explanations for their predictions, and as a means to evaluate the quality of model-generated explanations. In this review, we identify three predominant classes of explanations (highlights, free-text, and structured), organize the literature on annotating each type, point to what has been learned to date, and give recommendations for collecting ExNLP datasets in the future.

Clinical notes are text documents that are created by clinicians for each patient encounter. They are typically accompanied by medical codes, which describe the diagnosis and treatment. Annotating these codes is labor intensive and error prone; furthermore, the connection between the codes and the text is not annotated, obscuring the reasons and details behind specific diagnoses and treatments. We present an attentional convolutional network that predicts medical codes from clinical text. Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes. The method is accurate, achieving precision @ 8 of 0.7 and a Micro-F1 of 0.52, which are both significantly better than the prior state of the art. Furthermore, through an interpretability evaluation by a physician, we show that the attention mechanism identifies meaningful explanations for each code assignment.