论文检索

Social Aspects/Accountability, Transparency and Interpretability

Quentin Delfosse, Hikaru Shindo, Devendra Dhami, Kristian Kersting

The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's behavior, especially when working on the image level. Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place.Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE). NUDGE exploits trained neural network-based agents to guide the search of candidate-weighted logic rules, then uses differentiable logic to train the logic agents. Our experimental evaluation demonstrates that NUDGE agents can induce interpretable and explainable policies while outperforming purely neural ones and showing good flexibility to environments of different initial states and problem sizes.

Social Aspects/Accountability, Transparency and Interpretability

Yifan Zhang, Haowei He, Zhiquan Tan, Yang Yuan

In the current landscape of explanation methodologies, most predominant approaches, such as SHAP and LIME, employ removal-based techniques to evaluate the impact of individual features by simulating various scenarios with specific features omitted. Nonetheless, these methods primarily emphasize efficiency in the original context, often resulting in general inconsistencies. In this paper, we demonstrate that such inconsistency is an inherent aspect of these approaches by establishing the Impossible Trinity Theorem, which posits that interpretability, efficiency, and consistency cannot hold simultaneously. Recognizing that the attainment of an ideal explanation remains elusive, we propose the utilization of interpretation error as a metric to gauge inefficiencies and inconsistencies. To this end, we present two novel algorithms founded on the standard polynomial basis, aimed at minimizing interpretation error. Our empirical findings indicate that the proposed methods achieve a substantial reduction in interpretation error, up to 31.8 times lower when compared to alternative techniques.

Social Aspects/Accountability, Transparency and Interpretability

Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas

Do neural networks, trained on well-understood algorithmic tasks, reliably rediscover known algorithms? Several recent studies, on tasks ranging from group operations to in-context linear regression, have suggested that the answer is yes. Using modular addition as a prototypical problem, we show that algorithm discovery in neural networks is sometimes more complex: small changes to model hyperparameters and initializations can induce discovery of qualitatively different algorithms from a fixed training set, and even learning of multiple different solutions in parallel. In modular addition, we specifically show that models learn a known *Clock* algorithm, a previously undescribed, less intuitive, but comprehensible procedure we term the *Pizza* algorithm, and a variety of even more complex procedures. Our results show that even simple learning problems can admit a surprising diversity of solutions, motivating the development of new tools for mechanistically characterizing the behavior of neural networks across the algorithmic phase space.

Social Aspects/Accountability, Transparency and Interpretability

Michael Lepori, Thomas Serre, Ellie Pavlick

Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement. One possibility is that neural networks implicitly break down complex tasks into subroutines, implement modular solutions to these subroutines, and compose them into an overall solution to a task --- a property we term structural compositionality. Another possibility is that they may simply learn to match new inputs to learned templates, eliding task decomposition entirely. Here, we leverage model pruning techniques to investigate this question in both vision and language across a variety of architectures, tasks, and pretraining regimens. Our results demonstrate that models oftentimes implement solutions to subroutines via modular subnetworks, which can be ablated while maintaining the functionality of other subnetworks. This suggests that neural networks may be able to learn compositionality, obviating the need for specialized symbolic mechanisms.

Social Aspects/Accountability, Transparency and Interpretability

David Watson, Joshua O'Hara, Niek Tax, Richard Mudd, Ido Guy

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has received relatively little attention. We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs. We consider games with modified characteristic functions and find deep connections between the resulting Shapley values and fundamental quantities from information theory and conditional independence testing. We outline inference procedures for finite sample error rate control with provable guarantees, and implement efficient algorithms that perform well in a range of experiments on real and simulated data. Our method has applications to covariate shift detection, active learning, feature selection, and active feature-value acquisition.

Social Aspects/Accountability, Transparency and Interpretability

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman

Concept erasure aims to remove specified features from a representation. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We introduce LEAst-squares Concept Erasure (LEACE), a closed-form method which provably prevents all linear classifiers from detecting a concept while changing the representation as little as possible, as measured by a broad class of norms. We apply LEACE to large language models with a novel procedure called concept scrubbing, which erases target concept information from _every_ layer in the network. We demonstrate our method on two tasks: measuring the reliance of language models on part-of-speech information, and reducing gender bias in BERT embeddings. Our code is available at https://github.com/EleutherAI/concept-erasure.

Social Aspects/Accountability, Transparency and Interpretability

Julien Siems, Konstantin Ditschuneit, Winfried Ripken, Alma Lindborg, Maximilian Schambach, Johannes Otterbach, Martin Genzel

Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the target value as a sum of non-linear transformations of the features. Despite the current enthusiasm for GAMs, their susceptibility to concurvity — i.e., (possibly non-linear) dependencies between the features — has hitherto been largely overlooked. Here, we demonstrate how concurvity can severly impair the interpretability of GAMs and propose a remedy: a conceptually simple, yet effective regularizer which penalizes pairwise correlations of the non-linearly transformed feature variables. This procedure is applicable to any differentiable additive model, such as Neural Additive Models or NeuralProphet, and enhances interpretability by eliminating ambiguities due to self-canceling feature contributions. We validate the effectiveness of our regularizer in experiments on synthetic as well as real-world datasets for time-series and tabular data. Our experiments show that concurvity in GAMs can be reduced without significantly compromising prediction quality, improving interpretability and reducing variance in the feature importances.

Social Aspects/Accountability, Transparency and Interpretability

Sander Beckers

As more and more decisions that have a significant ethical dimension are being outsourced to AI systems, it is important to have a definition of _moral responsibility_ that can be applied to AI systems. Moral responsibility for an outcome of an agent who performs some action is commonly taken to involve both a _causal condition_ and an _epistemic condition_: the action should cause the outcome, and the agent should have been aware - in some form or other - of the possible moral consequences of their action. This paper presents a formal definition of both conditions within the framework of causal models. I compare my approach to the existing approaches of Braham and van Hees (BvH) and of Halpern and Kleiman-Weiner (HK). I then generalize my definition into a _degree of responsibility_.

Social Aspects/Accountability, Transparency and Interpretability

Shengbang Tong, Erik Jones, Jacob Steinhardt

Deployed multimodal models can fail in ways that evaluators did not anticipate. In order to find these failures before deployment, we introduce MultiMon, a system that automatically identifies systematic failures---generalizable, natural-language descriptions that describe categories of individual failures. To uncover systematic failures, MultiMon scrapes for examples of erroneous agreement: inputs that produce the same output, but should not. It then prompts a language model to identify common categories and describe them in natural language. We use MultiMon to find 14 systematic failures (e.g."ignores quantifiers'') of the CLIP text-encoder, each comprising hundreds of distinct inputs (e.g."a shelf with a few/many books''). Because CLIP is the backbone for most state-of-the-art multimodal models, these inputs produce failures in Midjourney 5.1, DALL-E, VideoFusion, and others. MultiMon can also steer towards failures relevant to specific use cases, such as self-driving cars. We see MultiMon as a step towards evaluation that autonomously explores the long-tail of potential system failures.

Social Aspects/Accountability, Transparency and Interpretability

Usha Bhalla, Suraj Srinivas, Himabindu Lakkaraju

With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model behaviour. To this end, two broad strategies have been outlined in prior literature to explain models. Post hoc explanation methods explain the behaviour of complex black-box models by identifying features critical to model predictions; however, prior work has shown that these explanations may not be faithful, in that they incorrectly attribute high importance to features that are unimportant or non-discriminative for the underlying task. Inherently interpretable models, on the other hand, circumvent these issues by explicitly encoding explanations into model architecture, meaning their explanations are naturally faithful, but they often exhibit poor predictive performance due to their limited expressive power. In this work, we identify a key reason for the lack of faithfulness of feature attributions: the lack of robustness of the underlying black-box models, especially the erasure of unimportant distractor features in the input. To address this issue, we propose Distractor Erasure Tuning (DiET), a method that adapts black-box models to be robust to distractor erasure, thus providing discriminative and faithful attributions. This strategy naturally combines the ease-of-use of post hoc explanations with the faithfulness of inherently interpretable models. We perform extensive experiments on semi-synthetic and real-world datasets, and show that DiET produces models that (1) closely approximate the original black-box models they are intended to explain, and (2) yield explanations that match approximate ground truths available by construction.

Social Aspects/Accountability, Transparency and Interpretability

Ao Sun, Pingchuan Ma, Yuanyuan Yuan, Shuai Wang

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying important pixels, and emerging concept-based XAI explore forming explanations with concepts (e.g., a head in an image). However, pixels are generally hard to interpret and sensitive to the imprecision of XAI methods, whereas “concepts” in prior works require human annotation or are limited to pre-defined concept sets. On the other hand, driven by large-scale pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promotable framework for performing precise and comprehensive instance segmentation, enabling automatic preparation of concept sets from a given image. This paper for the first time explores using SAM to augment concept-based XAI. We offer an effective and flexible concept-based explanation method, namely Explain Any Concept (EAC), which explains DNN decisions with any concept. While SAM is highly effective and offers an “out-of-the-box” instance segmentation, it is costly when being integrated into defacto XAI pipelines. We thus propose a lightweight per-input equivalent (PIE) scheme, enabling efficient explanation with a surrogate model. Our evaluation over two popular datasets (ImageNet and COCO) illustrate the highly encouraging performance of EAC over commonly-used XAI methods.

Social Aspects/Accountability, Transparency and Interpretability

Avani Gupta, Saurabh Saini, P J Narayanan

Humans use abstract *concepts* for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's sensitivity and possible biases to a given concept. We extend CAVs from post-hoc analysis to ante-hoc training to reduce model bias through fine-tuning using an additional *Concept Loss*. Concepts are defined on the final layer of the network in the past. We generalize it to intermediate layers, including the last convolution layer. We also introduce *Concept Distillation*, a method to define rich and effective concepts using a pre-trained knowledgeable model as the teacher. Our method can sensitize or desensitize a model towards concepts. We show applications of concept-sensitive training to debias several classification problems. We also show a way to induce prior knowledge into a reconstruction problem. We show that concept-sensitive training can improve model interpretability, reduce biases, and induce prior knowledge.

Social Aspects/Accountability, Transparency and Interpretability

Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat, Mihaela van der Schaar

Uncertainty quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods. We introduce the confusion density matrix---a kernel-based approximation of the misclassification density---and use this to categorize suspicious examples identified by a given uncertainty method into three classes: out-of-distribution (OOD) examples, boundary (Bnd) examples, and examples in regions of high in-distribution misclassification (IDM). Through extensive experiments, we show that our framework provides a new and distinct perspective for assessing differences between uncertainty quantification methods, thereby forming a valuable assessment benchmark.

Social Aspects/Accountability, Transparency and Interpretability

Stella Biderman, USVSN PRASHANTH, Lintang Sutawika, Hailey Schoelkopf, Quentin Anthony, Shivanshu Purohit, Edward Raff

Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for deploying language models. In particular, it is vital to minimize a model's memorization of sensitive datapoints such as those containing personal identifiable information (PII). The prevalence of such undesirable memorization can pose issues for model trainers, and may even require discarding an otherwise functional model. We therefore seek to predict which sequences will be memorized before a large model's full train-time by extrapolating the memorization behavior of lower-compute trial runs. We measure memorization in the Pythia model suite and plot scaling laws for forecasting memorization, allowing us to provide equi-compute recommendations to maximize the reliability (recall) of such predictions. We additionally provide further novel discoveries on the distribution of memorization scores across models and data. We release all code and data necessary to reproduce the results in this paper at https://github.com/EleutherAI/pythia.

Social Aspects/Accountability, Transparency and Interpretability

Jack Good, Torin Kovach, Kyle Miller, Artur Dubrawski

Decision trees are regarded for high interpretability arising from their hierarchical partitioning structure built on simple decision rules. However, in practice, this is not realized because axis-aligned partitioning of realistic data results in deep trees, and because ensemble methods are used to mitigate overfitting. Even then, model complexity and performance remain sensitive to transformation of the input, and extensive expert crafting of features from the raw data is common. We propose the first system to alternate sparse feature learning with differentiable decision tree construction to produce small, interpretable trees with good performance. We benchmark against conventional tree-based models and demonstrate several notions of interpretation of a model and its predictions.

Social Aspects/Accountability, Transparency and Interpretability

Arthur Conmy, Augustine Mavor-Parker, Aengus Lynch, Stefan Heimersheim, Adrià Garriga-Alonso

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors oftransformer models. This paper systematizes the mechanistic interpretability process they followed. First, researcherschoose a metric and dataset that elicit the desired model behavior. Then, they apply activation patching to find whichabstract neural network units are involved in the behavior. By varying the dataset, metric, and units underinvestigation, researchers can understand the functionality of each component.We automate one of the process' steps: finding the connections between the abstract neural network units that form a circuit. We propose several algorithms and reproduce previous interpretability results to validate them. Forexample, the ACDC algorithm rediscovered 5/5 of the component types in a circuit in GPT-2 Small that computes theGreater-Than operation. ACDC selected 68 of the 32,000 edges in GPT-2 Small, all of which were manually found byprevious work. Our code is available at https://github.com/ArthurConmy/Automatic-Circuit-Discovery

Social Aspects/Accountability, Transparency and Interpretability

Miles Turpin, Julian Michael, Ethan Perez, Samuel Bowman

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of transparency into LLMs' predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model's prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs—e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always "(A)"—which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods.

Social Aspects/Accountability, Transparency and Interpretability

Ryan Thompson, Amir Dezfouli, robert kohn

Sparse linear models are one of several core tools for interpretable machine learning, a field of emerging importance as predictive models permeate decision-making in many domains. Unfortunately, sparse linear models are far less flexible as functions of their input features than black-box models like deep neural networks. With this capability gap in mind, we study a not-uncommon situation where the input features dichotomize into two groups: explanatory features, which are candidates for inclusion as variables in an interpretable model, and contextual features, which select from the candidate variables and determine their effects. This dichotomy leads us to the contextual lasso, a new statistical estimator that fits a sparse linear model to the explanatory features such that the sparsity pattern and coefficients vary as a function of the contextual features. The fitting process learns this function nonparametrically via a deep neural network. To attain sparse coefficients, we train the network with a novel lasso regularizer in the form of a projection layer that maps the network's output onto the space of $\ell_1$-constrained linear models. An extensive suite of experiments on real and synthetic data suggests that the learned models, which remain highly transparent, can be sparser than the regular lasso without sacrificing the predictive power of a standard deep neural network.

Social Aspects/Accountability, Transparency and Interpretability

Ziyuan Ye, Rihan Huang, Qilin Wu, Quanying Liu

Post-hoc explanation techniques on graph neural networks (GNNs) provide economical solutions for opening the black-box graph models without model retraining. Many GNN explanation variants have achieved state-of-the-art explaining results on a diverse set of benchmarks, while they rarely provide theoretical analysis for their inherent properties and explanatory capability. In this work, we propose $\underline{\text{S}}$tructure-$\underline{\text{A}}$ware Shapley-based $\underline{\text{M}}$ultipiece $\underline{\text{E}}$xplanation (SAME) method to address the structure-aware feature interactions challenges for GNNs explanation. Specifically, SAME leverages an expansion-based Monte Carlo tree search to explore the multi-grained structure-aware connected substructure. Afterward, the explanation results are encouraged to be informative of the graph properties by optimizing the combination of distinct single substructures. With the consideration of fair feature interactions in the process of investigating multiple connected important substructures, the explanation provided by SAME has the potential to be as explainable as the theoretically optimal explanation obtained by the Shapley value within polynomial time. Extensive experiments on real-world and synthetic benchmarks show that SAME improves the previous state-of-the-art fidelity performance by 12.9\% on BBBP, 7.01\% on MUTAG, 42.3\% on Graph-SST2, 38.9\% on Graph-SST5, 11.3\% on BA-2Motifs and 18.2\% on BA-Shapes under the same testing condition. Code is available at https://github.com/same2023neurips/same.

Social Aspects/Accountability, Transparency and Interpretability

Dan Friedman, Alexander Wettig, Danqi Chen

Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approaches require considerable manual effort and still fall short of providing complete, faithful descriptions of the underlying algorithms. In this work, we introduce a procedure for training Transformers that are mechanistically interpretable by design. We build on RASP [Weiss et al., 2021], a programming language that can be compiled into Transformer weights. Instead of compiling human-written programs into Transformers, we design a modified Transformer that can be trained using gradient-based optimization and then automatically converted into a discrete, human-readable program. We refer to these models as Transformer Programs. To validate our approach, we learn Transformer Programs for a variety of problems, including an in-context learning task, a suite of algorithmic problems (e.g. sorting, recognizing Dyck languages), and NLP tasks including named entity recognition and text classification. The Transformer Programs can automatically find reasonable solutions, performing on par with standard Transformers of comparable size; and, more importantly, they are easy to interpret. To demonstrate these advantages, we convert Transformers into Python programs and use off-the-shelf code analysis tools to debug model errors and identify the “circuits” used to solve different sub-problems. We hope that Transformer Programs open a new path toward the goal of intrinsically interpretable machine learning.