Quan Ze Chen

Andre Ye, Quan Ze Chen, Amy Zhang · uw

Medical image segmentation modeling is a high-stakes task where understanding of uncertainty is crucial for addressing visual ambiguity. Prior work has developed segmentation models utilizing probabilistic or generative mechanisms to infer uncertainty from labels where annotators draw a singular boundary. However, as these annotations cannot represent an individual annotator's uncertainty, models trained on them produce uncertainty maps that are difficult to interpret. We propose a novel segmentation representation, Confidence Contours, which uses high- and low-confidence ``contours'' to capture uncertainty directly, and develop a novel annotation system for collecting contours. We conduct an evaluation on the Lung Image Dataset Consortium (LIDC) and a synthetic dataset. From an annotation study with 30 participants, results show that Confidence Contours provide high representative capacity without considerably higher annotator effort. We also find that general-purpose segmentation models can learn Confidence Contours at the same performance level as standard singular annotations. Finally, from interviews with 5 medical experts, we find that Confidence Contour maps are more interpretable than Bayesian maps due to representation of structural uncertainty.

K. J. Kevin Feng, Quan Ze Chen, Inyoung Cheong et al. · uw

Case studies commonly form the pedagogical backbone in law, ethics, and many other domains that face complex and ambiguous societal questions informed by human values. Similar complexities and ambiguities arise when we consider how AI should be aligned in practice: when faced with vast quantities of diverse (and sometimes conflicting) values from different individuals and communities, with whose values is AI to align, and how should AI do so? We propose a complementary approach to constitutional AI alignment, grounded in ideas from case-based reasoning (CBR), that focuses on the construction of policies through judgments on a set of cases. We present a process to assemble such a case repository by: 1) gathering a set of ``seed'' cases -- questions one may ask an AI system -- in a particular domain, 2) eliciting domain-specific key dimensions for cases through workshops with domain experts, 3) using LLMs to generate variations of cases not seen in the wild, and 4) engaging with the public to judge and improve cases. We then discuss how such a case repository could assist in AI alignment, both through directly acting as precedents to ground acceptable behaviors, and as a medium for individuals and communities to engage in moral reasoning around AI.

Inyoung Cheong, King Xia, K. J. Kevin Feng et al. · uw

Large language models (LLMs) are increasingly capable of providing users with advice in a wide range of professional domains, including legal advice. However, relying on LLMs for legal queries raises concerns due to the significant expertise required and the potential real-world consequences of the advice. To explore \textit{when} and \textit{why} LLMs should or should not provide advice to users, we conducted workshops with 20 legal experts using methods inspired by case-based reasoning. The provided realistic queries ("cases") allowed experts to examine granular, situation-specific concerns and overarching technical and legal constraints, producing a concrete set of contextual considerations for LLM developers. By synthesizing the factors that impacted LLM response appropriateness, we present a 4-dimension framework: (1) User attributes and behaviors, (2) Nature of queries, (3) AI capabilities, and (4) Social impacts. We share experts' recommendations for LLM response strategies, which center around helping users identify `right questions to ask' and relevant information rather than providing definitive legal judgments. Our findings reveal novel legal considerations, such as unauthorized practice of law, confidentiality, and liability for inaccurate advice, that have been overlooked in the literature. The case-based deliberation method enabled us to elicit fine-grained, practice-informed insights that surpass those from de-contextualized surveys or speculative principles. These findings underscore the applicability of our method for translating domain-specific professional knowledge and practices into policies that can guide LLM behavior in a more responsible direction.

Quan Ze Chen, K. J. Kevin Feng, Chan Young Park et al.

When different groups' values differ, one approach to model alignment is to steer models at inference time towards each group's preferences. However, techniques like in-context learning only consider similarity when drawing few-shot examples and not cross-group differences in values. We propose SPICA, a framework that accounts for group-level differences during in-context example retrieval. SPICA introduces three designs: scenario banks, group-informed retrieval metrics, and in-context alignment prompts. From an evaluation of SPICA on an alignment task collecting inputs from four demographic groups ($n = 544$), our metrics retrieve in-context examples that more closely match observed preferences, with the best prompt configuration using multiple contrastive responses to demonstrate examples. In an end-to-end evaluation ($n = 120$), we observe that SPICA is higher rated than similarity-based retrieval, with groups seeing up to a +0.16 point improvement on a 5 point scale. Additionally, gains from SPICA were more uniform, with all groups benefiting from alignment rather than only some. Finally, we find that while a group-agnostic approach can align to aggregated values, it is not most suited for divergent groups.

Andrew Konya, Aviv Ovadya, Kevin Feng et al.

We introduce a method to measure the alignment between public will and language model (LM) behavior that can be applied to fine-tuning, online oversight, and pre-release safety checks. Our `chain of alignment' (CoA) approach produces a rule based reward (RBR) by creating model behavior $\textit{rules}$ aligned to normative $\textit{objectives}$ aligned to $\textit{public will}$. This factoring enables a nonexpert public to directly specify their will through the normative objectives, while expert intelligence is used to figure out rules entailing model behavior that best achieves those objectives. We validate our approach by applying it across three different domains of LM prompts related to mental health. We demonstrate a public input process built on collective dialogues and bridging-based ranking that reliably produces normative objectives supported by at least $96\% \pm 2\%$ of the US public. We then show that rules developed by mental health experts to achieve those objectives enable a RBR that evaluates an LM response's alignment with the objectives similarly to human experts (Pearson's $r=0.841$, $AUC=0.964$). By measuring alignment with objectives that have near unanimous public support, these CoA RBRs provide an approximate measure of alignment between LM behavior and public will.

Teanna Barrett, Quan Ze Chen, Amy X. Zhang

To investigate the well-observed racial disparities in computer vision systems that analyze images of humans, researchers have turned to skin tone as more objective annotation than race metadata for fairness performance evaluations. However, the current state of skin tone annotation procedures is highly varied. For instance, researchers use a range of untested scales and skin tone categories, have unclear annotation procedures, and provide inadequate analyses of uncertainty. In addition, little attention is paid to the positionality of the humans involved in the annotation process--both designers and annotators alike--and the historical and sociological context of skin tone in the United States. Our work is the first to investigate the skin tone annotation process as a sociotechnical project. We surveyed recent skin tone annotation procedures and conducted annotation experiments to examine how subjective understandings of skin tone are embedded in skin tone annotation procedures. Our systematic literature review revealed the uninterrogated association between skin tone and race and the limited effort to analyze annotator uncertainty in current procedures for skin tone annotation in computer vision evaluation. Our experiments demonstrated that design decisions in the annotation procedure such as the order in which the skin tone scale is presented or additional context in the image (i.e., presence of a face) significantly affected the resulting inter-annotator agreement and individual uncertainty of skin tone annotations. We call for greater reflexivity in the design, analysis, and documentation of procedures for evaluation using skin tone.

Shagun Jhaver, Quan Ze Chen, Detlef Knauss et al.

Online social platforms centered around content creators often allow comments on content, where creators moderate the comments they receive. As creators can face overwhelming numbers of comments, with some of them harassing or hateful, platforms typically provide tools such as word filters for creators to automate aspects of moderation. From needfinding interviews with 19 creators about how they use existing tools, we found that they struggled with writing good filters as well as organizing and revisiting their filters, due to the difficulty of determining what the filters actually catch. To address these issues, we present FilterBuddy, a system that supports creators in authoring new filters or building from existing filter lists, as well as organizing their filters and visualizing what comments are captured over time. We conducted an early-stage evaluation of FilterBuddy with YouTube creators, finding that participants see FilterBuddy not just as a moderation tool, but also a means to organize their comments to better understand their audiences.