Uncertainty cues are inherent in natural human interaction, as they signal to communication partners how much they can rely on conveyed information. Humans subconsciously provide such signals both verbally (e.g., through expressions such as "maybe" or "I think") and non-verbally (e.g., by diverting their gaze). In contrast, artificial intelligence (AI)-based services and machine learning (ML) models such as ChatGPT usually do not disclose the reliability of answers to their users. In this paper, we explore the potential of combining ML models as powerful information sources with human means of expressing uncertainty to contextualize the information. We present a comprehensive pipeline that comprises (1) the human-centered collection of (non-)verbal uncertainty cues, (2) the transfer of cues to virtual agent videos, (3) the annotation of videos for perceived uncertainty, and (4) the subsequent training of a custom ML model that can generate uncertainty cues in virtual agent behavior. In a final step (5), the trained ML model is evaluated in terms of both fidelity and generalizability of the generated (non-)verbal uncertainty behavior.
https://doi.org/10.1145/3654777.3676454
Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the problems of the LLMs they evaluate, requiring further human validation. We present a mixed-initiative approach to “validate the validators”— aligning LLM-generated evaluation functions (be it prompts or code) with human requirements. Our interface, EvalGen, provides automated assistance to users in generating evaluation criteria and implementing assertions. While generating candidate implementations (Python functions, LLM grader prompts), EvalGen asks humans to grade a subset of LLM outputs; this feedback is used to select implementations that better align with user grades. A qualitative study finds overall support for EvalGen but underscores the subjectivity and iterative nature of alignment. In particular, we identify a phenomenon we dub criteria drift: users need criteria to grade outputs, but grading outputs helps users define criteria. What is more, some criteria appear dependent on the specific LLM outputs observed (rather than independent and definable a priori), raising serious questions for approaches that assume the independence of evaluation from observation of model outputs. We present our interface and implementation details, a comparison of our algorithm with a baseline approach, and implications for the design of future LLM evaluation assistants.
https://doi.org/10.1145/3654777.3676450
The emergent large language/multimodal models facilitate the evolution of mobile agents, especially in mobile UI task automation. However, existing evaluation approaches, which rely on human validation or established datasets to compare agent-predicted actions with predefined action sequences, are unscalable and unfaithful. To overcome these limitations, this paper presents LlamaTouch, a testbed for on-device mobile UI task execution and faithful, scalable task evaluation. By observing that the task execution process only transfers UI states, LlamaTouch employs a novel evaluation approach that only assesses whether an agent traverses all manually annotated, essential application/system states. LlamaTouch comprises three key techniques: (1) On-device task execution that enables mobile agents to interact with realistic mobile environments for task execution. (2) Fine-grained UI component annotation that merges pixel-level screenshots and textual screen hierarchies to explicitly identify and precisely annotate essential UI components with a rich set of designed annotation primitives. (3) A multi-level application state matching algorithm that utilizes exact and fuzzy matching to accurately detect critical information in each screen, even with unpredictable UI layout/content dynamics. LlamaTouch currently incorporates four mobile agents and 496 tasks, encompassing both tasks in the widely-used datasets and our self-constructed ones to cover more diverse mobile applications. Evaluation results demonstrate LlamaTouch’s high faithfulness of evaluation in real-world mobile environments and its better scalability than human validation. LlamaTouch also enables easy task annotation and integration of new mobile agents. Code and dataset are publicly available at https://github.com/LlamaTouch/LlamaTouch.
https://doi.org/10.1145/3654777.3676382
The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide additional information beyond the training data. Prior methods incorporate additional instance-level supervision, such as labels for misleading features or additional labels for debiased data. However, such strategies require a large amount of labeler effort. We hypothesize that people are good at providing textual feedback at the concept level, a capability that existing teaching frameworks do not leverage. We propose Clarify, a novel interface and method for interactively correcting model misconceptions. Through Clarify, users need only provide a short text description of a model's consistent failure patterns. Then, in an entirely automated way, we use such descriptions to improve the training process. Clarify is the first end-to-end system for user model correction. Our user studies show that non-expert users can successfully describe model misconceptions via Clarify, leading to increased worst-case performance in two datasets. We additionally conduct a case study on a large-scale image dataset, ImageNet, using Clarify to find and rectify 31 novel hard subpopulations.
https://doi.org/10.1145/3654777.3676362
Fact-checking data claims requires data evidence retrieval and analysis, which can become tedious and intractable when done manually. This work presents Aletheia, an automated fact-checking prototype designed to facilitate data claims verification and enhance data evidence communication. For verification, we utilize a pre-trained LLM to parse the semantics for evidence retrieval. To effectively communicate the data evidence, we design representations in two forms: data tables and visualizations, tailored to various data fact types. Additionally, we design interactions that showcase a real-world application of these techniques. We evaluate the performance of two core NLP tasks with a curated dataset comprising 400 data claims and compare the two representation forms regarding viewers’ assessment time, confidence, and preference via a user study with 20 participants. The evaluation offers insights into the feasibility and bottlenecks of using LLMs for data fact-checking tasks, potential advantages and disadvantages of using visualizations over data tables, and design recommendations for presenting data evidence.
https://doi.org/10.1145/3654777.3676359