The rise of foundation models holds immense promise for advancing AI, but this progress may amplify existing risks and inequalities, leaving marginalized communities behind. In this position paper, we discuss that disparities towards marginalized communities – performance, representation, privacy, robustness, interpretability and safety – are not isolated concerns but rather interconnected elements of a cascading disparity phenomenon. We contrast foundation models with traditional models and highlight the potential for exacerbated disparity against marginalized communities. Moreover, we emphasize the unique threat of cascading impacts in foundation models, where interconnected disparities can trigger long-lasting negative consequences, specifically to the people on the margin. We define marginalized communities within the machine learning context and explore the multifaceted nature of disparities. We analyze the sources of these disparities, tracing them from data creation, training and deployment procedures to highlight the complex technical and socio-technical landscape. To mitigate the pressing crisis, we conclude with a set of calls to action to mitigate disparity at its source.
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Deep Learning · Large Language Models
Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In particular, we develop in closed form $(i)$ the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and $(ii)$ the partition and per-region affine mappings of the feedforward (MLP) network of LLMs' layers. Our theoretical findings further enable the design of novel principled solutions applicable to state-of-the-art LLMs. First, we show that, through our geometric understanding, we can bypass LLMs' RLHF protection by controlling the embedding's intrinsic dimension through informed prompt manipulation. Second, we derive interpretable geometrical features that can be extracted from any (pre-trained) LLM, providing a rich abstract representation of their inputs. We observe that these features are sufficient to help solve toxicity detection, and even allow the identification of various types of toxicity. Our results demonstrate how, even in large-scale regimes, exact theoretical results can answer practical questions in LLMs. Code: https://github.com/RandallBalestriero/SplineLLM
Social Aspects · Accountability, Transparency and Interpretability
It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network's general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a "trace" of the network's execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.
Deep Learning · Other Representation Learning
Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics and cosmic structures. Thus, identifying sources of asymmetry is an important tool for understanding physical systems. In this paper, we focus on learning asymmetries of data using relaxed group convolutions. We provide both theoretical and empirical evidence that this flexible convolution technique allows the model to maintain the highest level of equivariance that is consistent with data and discover the subtle symmetry-breaking factors in various physical systems. We employ various relaxed group convolution architectures to uncover various symmetry-breaking factors that are interpretable and physically meaningful in different physical systems, including the phase transition of crystal structure, the isotropy and homogeneity breaking in turbulent flow, and the time-reversal symmetry breaking in pendulum systems.
Social Aspects · Trustworthy Machine Learning
Reinforcement learning can provide effective reasoning for sequential decision-making problems with variable dynamics. Such reasoning in practical implementation, however, poses a persistent challenge in interpreting the reward function and the corresponding optimal policy. Consequently, representing sequential decision-making problems as probabilistic inference can have considerable value, as, in principle, the inference offers diverse and powerful mathematical tools to infer the stochastic dynamics whilst suggesting a probabilistic interpretation of policy optimization. In this study, we propose a novel Adaptive Wasserstein Variational Optimization, namely AWaVO, to tackle these interpretability challenges. Our approach uses formal methods to achieve the interpretability: convergence guarantee, training transparency, and intrinsic decision-interpretation. To demonstrate its practicality, we showcase guaranteed interpretability including a global convergence rate $\Theta(1/\sqrt{T})$ not only in simulation but also in real-world quadrotor tasks. In comparison with state-of-the-art benchmarks, including TRPO-IPO, PCPO, and CRPO, we empirically verify that AWaVO offers a reasonable trade-off between high performance and sufficient interpretability.
Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
PDF ↗Social Aspects · Accountability, Transparency and Interpretability
In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network (ProtoPNet), which attempts to classify images based on meaningful parts of the input. While this architecture is able to produce visually interpretable classifications, it often learns to classify based on parts of the image that are not semantically meaningful. To address this problem, we propose the Reward Reweighing, Reselecting, and Retraining (R3) post-processing framework, which performs three additional corrective updates to a pretrained ProtoPNet in an offline and efficient manner. The first two steps involve learning a reward model based on collected human feedback and then aligning the prototypes with human preferences. The final step is retraining, which realigns the base features and the classifier layer of the original model with the updated prototypes. We find that our R3 framework consistently improves both the interpretability and the predictive accuracy of ProtoPNet and its variants.
Social Aspects · Trustworthy Machine Learning
In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability of adversarial prompts. The computational efficiency of BEAST facilitates us to investigate its applications on LMs for jailbreaking, eliciting hallucinations, and privacy attacks. Our gradient-free targeted attack can jailbreak aligned LMs with high attack success rates within one minute. For instance, BEAST can jailbreak Vicuna-7B-v1.5 under one minute with a success rate of 89% when compared to a gradient-based baseline that takes over an hour to achieve 70% success rate using a single Nvidia RTX A6000 48GB GPU. BEAST can also generate adversarial suffixes for successful jailbreaks that can transfer to unseen prompts and unseen models such as GPT-4-Turbo. Additionally, we discover a unique outcome wherein our untargeted attack induces hallucinations in LM chatbots. Through human evaluations, we find that our untargeted attack causes Vicuna-7B-v1.5 to produce $\sim$15% more incorrect outputs when compared to LM outputs in the absence of our attack. We also learn that 22% of the time, BEAST causes Vicuna to generate outputs that are not relevant to the original prompt. Further, we use BEAST to generate adversarial prompts in a few seconds that can boost the performance of existing membership inference attacks for LMs. We believe that our fast attack, BEAST, has the potential to accelerate research in LM security and privacy.
Deep Learning · Large Language Models
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty, resulting from missing information in the model's training data. In large language models (LLMs) specifically, identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability, but remains an important open research question. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling, which can be applied to any pre-trained LLM. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions. We show that, when aleatoric uncertainty arises from ambiguity or under-specification in LLM inputs, this approach makes it possible to factor an (un-clarified) LLM's predictions into separate aleatoric and epistemic terms, using a decomposition similar to the one employed by Bayesian neural networks. Empirical evaluations demonstrate that input clarification ensembling provides accurate and reliable uncertainty quantification on several language processing tasks. Code and data are available at https://github.com/UCSB-NLP-Chang/llm_uncertainty.
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
PDF ↗Deep Learning
In-context learning is a powerful emergent ability in transformer models. Prior work in mechanistic interpretability has identified a circuit element that may be critical for in-context learning – the induction head (IH), which performs a match-and-copy operation. During training of large transformers on natural language data, IHs emerge around the same time as a notable phase change in the loss. Despite the robust evidence for IHs and this interesting coincidence with the phase change, relatively little is known about the diversity and emergence dynamics of IHs. Why is there more than one IH, and how are they dependent on each other? Why do IHs appear all of a sudden, and what are the subcircuits that enable them to emerge? We answer these questions by studying IH emergence dynamics in a controlled setting by training on synthetic data. In doing so, we develop and share a novel optogenetics-inspired causal framework for modifying activations throughout training. Using this framework, we delineate the diverse and additive nature of IHs. By "clamping" subsets of activations throughout training, we then identify three underlying subcircuits that interact to drive IH formation, yielding the phase change. Furthermore, these subcircuits shed light on data-dependent properties of formation, such as phase change timing, already showing the promise of this more in-depth understanding of subcircuits that need to "go right" for an induction head.
Reinforcement Learning · Deep RL
To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language---language like "this button turns on the TV" or "I put the bowls away"---that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that *agents should interpret such diverse language as a signal that helps them predict the future*: what they will observe, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations, and learns to act from imagined model rollouts. While current methods that learn language-conditioned policies degrade in performance with more diverse types of language, we show that Dynalang learns to leverage environment descriptions, game rules, and instructions to excel on tasks ranging from game-playing to navigating photorealistic home scans. Finally, we show that our method enables additional capabilities due to learning a generative model: Dynalang can be pretrained on text-only data, enabling learning from offline datasets, and generate language grounded in an environment.
Social Aspects · Accountability, Transparency and Interpretability
Traveling waves are a fundamental phenomenon in the brain, playing a crucial role in short-term information storage. In this study, we leverage the concept of traveling wave dynamics within a neural lattice to formulate a theoretical model of neural working memory in Recurrent Neural Networks (RNNs), study its properties, and its real world implications in AI. The proposed model diverges from traditional approaches, which assume information storage in static, register-like locations updated by interference. Instead, the model stores data as waves that is updated by the wave's boundary conditions. We rigorously examine the model's capabilities in representing and learning state histories, which are vital for learning history-dependent dynamical systems. The findings reveal that the model reliably stores external information and enhances the learning process by addressing the diminishing gradient problem of RNNs. To understand the model's real-world applicability, we explore two cases: linear boundary condition and non-linear, self-attention-driven boundary condition. The experiments reveal that the linear scenario is effectively *learned* by RNNs through backpropagation when modeling history-dependent dynamical systems. Conversely, the non-linear scenario parallels an attention-only transformer. Collectively, our findings suggest the broader relevance of traveling waves in AI and its potential in advancing neural network architectures.
Deep Learning · Everything Else
Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information from the original dataset. While distilled data can be used to train high performing models, little is understood about how the information is stored. In this study, we posit and answer three questions about the behavior, representativeness, and point-wise information content of distilled data. We reveal distilled data cannot serve as a substitute for real data during training outside the standard evaluation setting for dataset distillation. Additionally, the distillation process retains high task performance by compressing information related to the early training dynamics of real models. Finally, we provide an framework for interpreting distilled data and reveal that individual distilled data points contain meaningful semantic information. This investigation sheds light on the intricate nature of distilled data, providing a better understanding on how they can be effectively utilized.
Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory consumption caused by BP. Among the existing solutions, local learning optimizes gradient-isolated modules of a neural network with local errors and has been proved to be effective even on large-scale datasets. However, the reconciliation among local errors has never been investigated. In this paper, we first theoretically study non-greedy layer-wise training and show that the convergence cannot be assured when the local gradient in a module w.r.t. its input is not reconciled with the local gradient in the previous module w.r.t. its output. Inspired by the theoretical result, we further propose a local training strategy that successively regularizes the gradient reconciliation between neighboring modules without breaking gradient isolation or introducing any learnable parameters. Our method can be integrated into both local-BP and BP-free settings. In experiments, we achieve significant performance improvements compared to previous methods. Particularly, our method for CNN and Transformer architectures on ImageNet is able to attain a competitive performance with global BP, saving more than 40% memory consumption.
Miscellaneous Aspects of Machine Learning · Causality
We consider the effect of temporal aggregation on instantaneous (non-temporal) causal discovery in general setting. This is motivated by the observation that the true causal time lag is often considerably shorter than the observational interval. This discrepancy leads to high aggregation, causing time-delay causality to vanish and instantaneous dependence to manifest. Although we expect such instantaneous dependence has consistency with the true causal relation in certain sense to make the discovery results meaningful, it remains unclear what type of consistency we need and when will such consistency be satisfied. We proposed functional consistency and conditional independence consistency in formal way correspond functional causal model-based methods and conditional independence-based methods respectively and provide the conditions under which these consistencies will hold. We show theoretically and experimentally that causal discovery results may be seriously distorted by aggregation especially in complete nonlinear case and we also find causal relationship still recoverable from aggregated data if we have partial linearity or appropriate prior. Our findings suggest community should take a cautious and meticulous approach when interpreting causal discovery results from such data and show why and when aggregation will distort the performance of causal discovery methods.
Deep Learning · Graph Neural Networks
A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the optimization of GNNs through gradient descent implicitly leverages the graph structure to update the learned function. This phenomenon is dubbed as kernel-graph alignment, which has been empirically and theoretically corroborated. This new analytical framework from the optimization perspective enables interpretable explanations of when and why the learned GNN functions generalize, which are relevant to their limitations on heterophilic graphs. From a practical standpoint, it also provides high-level principles for designing new algorithms. We exemplify this by showing that a simple and efficient non-parametric algorithm, obtained by explicitly using graph structure to update the learned function, can consistently compete with nonlinear GNNs.
Deep Learning · Large Language Models
Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden states that are sparse, discrete, and more interpretable by quantizing their continuous features into what we call codebook features. Codebook features are produced by finetuning neural networks with vector quantization bottlenecks at each layer, producing a network whose hidden features are the sum of a small number of discrete vector codes chosen from a larger codebook. Surprisingly, we find that neural networks can operate under this extreme bottleneck with only modest degradation in performance. In addition, we can control a model's behavior by finding codes that activate on a desired behavior, then activating those same codes during generation. We first validate codebook features on a finite state machine dataset with far more hidden states than neurons. In this setting, our approach overcomes the superposition problem by assigning states to distinct codes, and we find that we can make the neural network behave as if it is in a different state by activating the code for that state. We then train Transformer language models with up to 410M parameters on two natural language datasets. We identify codes in these models representing diverse, disentangled concepts (ranging from negative emotions to months of the year) and find that we can guide the model to generate different topics and pronoun genders by activating these codes during inference. Overall, codebook features appear to be a promising unit of analysis and control for neural networks and interpretability. Our codebase and models are open-sourced at [this URL](https://github.com/taufeeque9/codebook-features).
Applications · Chemistry and Drug Discovery
Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely on more complex molecular structures with fewer examples that are carefully designed using known substructures. We propose a data-efficient and interpretable model for representing and reasoning over such molecules in terms of graph grammars that explicitly describe the hierarchical design space featuring motifs to be the design basis. We present a novel representation in the form of random walks over the design space, which facilitates both molecule generation and property prediction. We demonstrate clear advantages over existing methods in terms of performance, efficiency, and synthesizability of predicted molecules, and we provide detailed insights into the method's chemical interpretability.
Constructing valid prediction intervals rather than point estimates is a well-established approach for uncertainty quantification in the regression setting. Models equipped with this capacity output an interval of values in which the ground truth target will fall with some prespecified probability. This is an essential requirement in many real-world applications where simple point predictions' inability to convey the magnitude and frequency of errors renders them insufficient for high-stakes decisions. Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the (non-parametric) distribution of outputs. This method is simple, computationally inexpensive, interpretable, assumption-free, and effective. However, it does require that the specific quantiles being learned are chosen a priori. This results in (a) intervals that are arbitrarily symmetric around the median which is sub-optimal for realistic skewed distributions, or (b) learning an excessive number of intervals. In this work, we propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint whilst maintaining its strengths. We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities (e.g. mean width) whilst retaining the essential coverage guarantees of quantile regression.
Applications · Computer Vision
Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a Gradient-based visual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the superiority of Grad-ECLIP compared with the state-of-the-art methods. A series of analysis are conducted based on our visual explanation results, from which we explore the working mechanism of image-text matching, and the strengths and limitations in attribution identification of CLIP. Codes are available here: https://github.com/Cyang-Zhao/Grad-Eclip.
Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
PDF ↗Social Aspects · Accountability, Transparency and Interpretability
Pre-trained language models (PLMs) are commonly used for various downstream natural language processing tasks via fine-tuning. However, recent studies have demonstrated that PLMs are vulnerable to backdoor attacks, which can mislabel poisoned samples to target outputs even after a vanilla fine-tuning process. The key challenge for defending against the backdoored PLMs is that end users who adopt the PLMs for their downstream tasks usually do not have any knowledge about the attacking strategies, such as triggers. To tackle this challenge, in this work, we propose a backdoor mitigation approach, PURE, via head pruning and normalization of attention weights. The idea is to prune the attention heads that are potentially affected by poisoned texts with only clean texts on hand and then further normalize the weights of remaining attention heads to mitigate the backdoor impacts. We conduct experiments to defend against various backdoor attacks on the classification task. The experimental results show the effectiveness of PURE in lowering the attack success rate without sacrificing the performance on clean texts.