Searcharxiv⌕ Search

arXiv subjects

Mennatallah El-Assady

Publications and source records attributed to Mennatallah El-Assady.

At least 73 records · Page 4Linked to original sources

Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges

The growing popularity of generative language models has amplified interest in interactive methods to guide model outputs. Prompt refinement is considered one of the most effective means to influence output among these methods. We identify several challenges associated with prompting large language models, categorized into data- and model-specific, linguistic, and socio-linguistic challenges. A comprehensive examination of model outputs, including runner-up candidates and their corresponding probabilities, is needed to address these issues. The beam search tree, the prevalent algorithm to sample model outputs, can inherently supply this information. Consequently, we introduce an interactive visual method for investigating the beam search tree, facilitating analysis of the decisions made by the model during generation. We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges. Our methodology validates existing results and offers additional insights.

cs.CL↗

A Heuristic Approach for Dual Expert/End-User Evaluation of Guidance in Visual Analytics

Guidance can support users during the exploration and analysis of complex data. Previous research focused on characterizing the theoretical aspects of guidance in visual analytics and implementing guidance in different scenarios. However, the evaluation of guidance-enhanced visual analytics solutions remains an open research question. We tackle this question by introducing and validating a practical evaluation methodology for guidance in visual analytics. We identify eight quality criteria to be fulfilled and collect expert feedback on their validity. To facilitate actual evaluation studies, we derive two sets of heuristics. The first set targets heuristic evaluations conducted by expert evaluators. The second set facilitates end-user studies where participants actually use a guidance-enhanced system. By following such a dual approach, the different quality criteria of guidance can be examined from two different perspectives, enhancing the overall value of evaluation studies. To test the practical utility of our methodology, we employ it in two studies to gain insight into the quality of two guidance-enhanced visual analytics solutions, one being a work-in-progress research prototype, and the other being a publicly available visualization recommender system. Based on these two evaluations, we derive good practices for conducting evaluations of guidance in visual analytics and identify pitfalls to be avoided during such studies.

cs.HC↗

RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback

To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback and to consider human factors involved in providing feedback of different types. However, the systematic study of learning from diverse types of feedback is held back by limited standardized tooling available to researchers. To bridge this gap, we propose RLHF-Blender, a configurable, interactive interface for learning from human feedback. RLHF-Blender provides a modular experimentation framework and implementation that enables researchers to systematically investigate the properties and qualities of human feedback for reward learning. The system facilitates the exploration of various feedback types, including demonstrations, rankings, comparisons, and natural language instructions, as well as studies considering the impact of human factors on their effectiveness. We discuss a set of concrete research opportunities enabled by RLHF-Blender. More information is available at https://rlhfblender.info/.

cs.LG↗

Visual Explanations with Attributions and Counterfactuals on Time Series Classification

With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.

cs.HC↗

Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals

We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions. The dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3 suggestions. Additionally, users can receive feedback from a trained NLI model on how challenging the newly created example is and make refinements based on the feedback. Through our investigation, we discover several categories of spurious correlations that impact the reasoning of NLI models, which we group into three categories: Semantic Relevance, Logical Fallacies, and Bias. Based on our findings, we identify and describe various research opportunities, including diversifying training data and assessing NLI models' robustness by creating adversarial test suites.

cs.CL↗

Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings

Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based clinical diagnostics, it is necessary to integrate explainable AI into these safety-critical systems. Current explanatory methods typically assign attribution scores to pixel regions in the input image, indicating their importance for a model's decision. However, they fall short when explaining why a visual feature is used. We propose a framework that utilizes interpretable disentangled representations for downstream-task prediction. Through visualizing the disentangled representations, we enable experts to investigate possible causation effects by leveraging their domain knowledge. Additionally, we deploy a multi-path attribution mapping for enriching and validating explanations. We demonstrate the effectiveness of our approach on a synthetic benchmark suite and two medical datasets. We show that the framework not only acts as a catalyst for causal relation extraction but also enhances model robustness by enabling shortcut detection without the need for testing under distribution shifts.

cs.CV↗

Automatic Generation of Socratic Subquestions for Teaching Math Word Problems

Socratic questioning is an educational method that allows students to discover answers to complex problems by asking them a series of thoughtful questions. Generation of didactically sound questions is challenging, requiring understanding of the reasoning process involved in the problem. We hypothesize that such questioning strategy can not only enhance the human performance, but also assist the math word problem (MWP) solvers. In this work, we explore the ability of large language models (LMs) in generating sequential questions for guiding math word problem-solving. We propose various guided question generation schemes based on input conditioning and reinforcement learning. On both automatic and human quality evaluations, we find that LMs constrained with desirable question properties generate superior questions and improve the overall performance of a math word problem solver. We conduct a preliminary user study to examine the potential value of such question generation models in the education domain. Results suggest that the difficulty level of problems plays an important role in determining whether questioning improves or hinders human performance. We discuss the future of using such questioning strategies in education.

cs.CL↗

How to Enable Uncertainty Estimation in Proximal Policy Optimization

While deep reinforcement learning (RL) agents have showcased strong results across many domains, a major concern is their inherent opaqueness and the safety of such systems in real-world use cases. To overcome these issues, we need agents that can quantify their uncertainty and detect out-of-distribution (OOD) states. Existing uncertainty estimation techniques, like Monte-Carlo Dropout or Deep Ensembles, have not seen widespread adoption in on-policy deep RL. We posit that this is due to two reasons: concepts like uncertainty and OOD states are not well defined compared to supervised learning, especially for on-policy RL methods. Secondly, available implementations and comparative studies for uncertainty estimation methods in RL have been limited. To overcome the first gap, we propose definitions of uncertainty and OOD for Actor-Critic RL algorithms, namely, proximal policy optimization (PPO), and present possible applicable measures. In particular, we discuss the concepts of value and policy uncertainty. The second point is addressed by implementing different uncertainty estimation methods and comparing them across a number of environments. The OOD detection performance is evaluated via a custom evaluation benchmark of in-distribution (ID) and OOD states for various RL environments. We identify a trade-off between reward and OOD detection performance. To overcome this, we formulate a Pareto optimization problem in which we simultaneously optimize for reward and OOD detection performance. We show experimentally that the recently proposed method of Masksembles strikes a favourable balance among the survey methods, enabling high-quality uncertainty estimation and OOD detection while matching the performance of original RL agents.

cs.LG↗

Characterizing Uncertainty in the Visual Text Analysis Pipeline

Current visual text analysis approaches rely on sophisticated processing pipelines. Each step of such a pipeline potentially amplifies any uncertainties from the previous step. To ensure the comprehensibility and interoperability of the results, it is of paramount importance to clearly communicate the uncertainty not only of the output but also within the pipeline. In this paper, we characterize the sources of uncertainty along the visual text analysis pipeline. Within its three phases of labeling, modeling, and analysis, we identify six sources, discuss the type of uncertainty they create, and how they propagate.

cs.HC↗

BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning

Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be safety-critic or impactful in the real world. We investigate the susceptibility of vision-based reinforcement learning agents to gradient-based adversarial attacks and evaluate a potential defense. We observe that Bottleneck Attention Modules (BAM) included in CNN architectures can act as potential tools to increase robustness against adversarial attacks. We show how learned attention maps can be used to recover activations of a convolutional layer by restricting the spatial activations to salient regions. Across a number of RL environments, BAM-enhanced architectures show increased robustness during inference. Finally, we discuss potential future research directions.

cs.LG↗

Visual Comparison of Language Model Adaptation

Neural language models are widely used; however, their model parameters often need to be adapted to the specific domains and tasks of an application, which is time- and resource-consuming. Thus, adapters have recently been introduced as a lightweight alternative for model adaptation. They consist of a small set of task-specific parameters with a reduced training time and simple parameter composition. The simplicity of adapter training and composition comes along with new challenges, such as maintaining an overview of adapter properties and effectively comparing their produced embedding spaces. To help developers overcome these challenges, we provide a twofold contribution. First, in close collaboration with NLP researchers, we conducted a requirement analysis for an approach supporting adapter evaluation and detected, among others, the need for both intrinsic (i.e., embedding similarity-based) and extrinsic (i.e., prediction-based) explanation methods. Second, motivated by the gathered requirements, we designed a flexible visual analytics workspace that enables the comparison of adapter properties. In this paper, we discuss several design iterations and alternatives for interactive, comparative visual explanation methods. Our comparative visualizations show the differences in the adapted embedding vectors and prediction outcomes for diverse human-interpretable concepts (e.g., person names, human qualities). We evaluate our workspace through case studies and show that, for instance, an adapter trained on the language debiasing task according to context-0 (decontextualized) embeddings introduces a new type of bias where words (even gender-independent words such as countries) become more similar to female than male pronouns. We demonstrate that these are artifacts of context-0 embeddings.

cs.AI↗

Lotse: A Practical Framework for Guidance in Visual Analytics

Co-adaptive guidance aims to enable efficient human-machine collaboration in visual analytics, as proposed by multiple theoretical frameworks. This paper bridges the gap between such conceptual frameworks and practical implementation by introducing an accessible model of guidance and an accompanying guidance library, mapping theory into practice. We contribute a model of system-provided guidance based on design templates and derived strategies. We instantiate the model in a library called Lotse that allows specifying guidance strategies in definition files and generates running code from them. Lotse is the first guidance library using such an approach. It supports the creation of reusable guidance strategies to retrofit existing applications with guidance and fosters the creation of general guidance strategy patterns. We demonstrate its effectiveness through first-use case studies with VA researchers of varying guidance design expertise and find that they are able to effectively and quickly implement guidance with Lotse. Further, we analyze our framework's cognitive dimensions to evaluate its expressiveness and outline a summary of open research questions for aligning guidance practice with its intricate theory.

cs.HC↗

Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language

Language models learn and represent language differently than humans; they learn the form and not the meaning. Thus, to assess the success of language model explainability, we need to consider the impact of its divergence from a user's mental model of language. In this position paper, we argue that in order to avoid harmful rationalization and achieve truthful understanding of language models, explanation processes must satisfy three main conditions: (1) explanations have to truthfully represent the model behavior, i.e., have a high fidelity; (2) explanations must be complete, as missing information distorts the truth; and (3) explanations have to take the user's mental model into account, progressively verifying a person's knowledge and adapting their understanding. We introduce a decision tree model to showcase potential reasons why current explanations fail to reach their objectives. We further emphasize the need for human-centered design to explain the model from multiple perspectives, progressively adapting explanations to changing user expectations.

cs.CL↗

From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process

Explainable AI (XAI) is a necessity in safety-critical systems such as in clinical diagnostics due to a high risk for fatal decisions. Currently, however, XAI resembles a loose collection of methods rather than a well-defined process. In this work, we elaborate on conceptual similarities between the largest subgroup of XAI, interpretable machine learning (IML), and classical statistics. Based on these similarities, we present a formalization of IML along the lines of a statistical process. Adopting this statistical view allows us to interpret machine learning models and IML methods as sophisticated statistical tools. Based on this interpretation, we infer three key questions, which we identify as crucial for the success and adoption of IML in safety-critical settings. By formulating these questions, we further aim to spark a discussion about what distinguishes IML from classical statistics and what our perspective implies for the future of the field.

cs.CV↗

Communication Analysis through Visual Analytics: Current Practices, Challenges, and New Frontiers

The automated analysis of digital human communication data often focuses on specific aspects such as content or network structure in isolation. This can provide limited perspectives while making cross-methodological analyses, occurring in domains like investigative journalism, difficult. Communication research in psychology and the digital humanities instead stresses the importance of a holistic approach to overcome these limiting factors. In this work, we conduct an extensive survey on the properties of over forty semi-automated communication analysis systems and investigate how they cover concepts described in theoretical communication research. From these investigations, we derive a design space and contribute a conceptual framework based on communication research, technical considerations, and the surveyed approaches. The framework describes the systems' properties, capabilities, and composition through a wide range of criteria organized in the dimensions (1) Data, (2) Processing and Models, (3) Visual Interface, and (4) Knowledge Generation. These criteria enable a formalization of digital communication analysis through visual analytics, which, we argue, is uniquely suited for this task by tackling automation complexity while leveraging domain knowledge. With our framework, we identify shortcomings and research challenges, such as group communication dynamics, trust and privacy considerations, and holistic approaches. Simultaneously, our framework supports the evaluation of systems and promotes the mutual exchange between researchers through a structured common language, laying the foundations for future research on communication analysis.

cs.HC↗

Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning

Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide. Instead, recently, more work has explored learning what to do from interacting with humans. So far, most of these approaches model humans as being (nosily) rational and, in particular, giving unbiased feedback. We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. In particular, we argue that human models have to be personal, contextual, and dynamic. This paper calls for research from different disciplines to address key questions about how humans provide feedback to AIs and how we can build more robust human-in-the-loop RL systems.

cs.LG↗

Characterizing Grounded Theory Approaches in Visualization

Grounded theory (GT) is a research methodology that entails a systematic workflow for theory generation grounded on emergent data. In this paper, we juxtapose GT workflows with typical workflows in visualization and visual analytics, shortly VIS, and underline the characteristics shared by these workflows. We explore the research landscape of VIS to observe where GT has been applied to generate VIS theories, explicitly as well as implicitly. We propose a "why" typology for characterizing aspects in VIS where GT can potentially play a significant role. We outline a "how" methodology for conducting GT research in VIS, which addresses the need for theoretical advancement in VIS while benefitting from other methods and techniques in VIS. We exemplify this "how" methodology by adopting GT approaches in studying the messages posted on VisGuides - an Open Discourse Forum for discussing visualization guidelines.

cs.HC↗

CorpusVis: Visual Analysis of Digital Sheet Music Collections

Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information. However, applying sophisticated algorithmic methods would require advanced technical expertise that analysts do not necessarily have. Bridging this gap, we contribute CorpusVis, an interactive visual workspace, enabling scalable and multi-faceted analysis. Our proposed visual analytics dashboard provides access to computational methods, generating varying perspectives on the same data. The proposed application uses metadata including composers, type, epoch, and low-level features, such as pitch, melody, and rhythm. To evaluate our approach, we conducted a pair analytics study with nine participants. The qualitative results show that CorpusVis supports users in performing exploratory and confirmatory analysis, leading them to new insights and findings. In addition, based on three exemplary workflows, we demonstrate how to apply our approach to different tasks, such as exploring musical features or comparing composers.

cs.HC↗