HEAL is back for its third iteration at CHI 2026! This workshop addresses the ongoing "evaluation crisis" in LLM research and practice by bringing together HCI and AI researchers to rethink LLM evaluation and auditing from a human-centered perspective.

Building on successful workshops at CHI 2024 and CHI 2025, we continue exploring topics around understanding stakeholders' needs and goals, establishing human-centered evaluation and auditing methods, developing tools and resources, and fostering community collaboration.

AI Agents-in-the-Loop: As practitioners increasingly turn to AI agents as evaluation partners, we must critically examine how to maintain human-centered approaches while leveraging agent capabilities for scale and efficiency. This year's theme explores the emerging frontier where human judgment meets agent automation—addressing fundamental questions about task allocation, meta-evaluation of evaluator agents, and the design of safeguards that preserve human agency while benefiting from automation.

Submission deadline: February 13, 2026 (AoE)

Notification of acceptance: March 13, 2026 (AoE)

Workshop date: April 13-17, 2026

Workshop location: Barcelona, Spain (In-person)

Contact: heal.workshop@gmail.com

We welcome participants working on human-centered evaluation and auditing of language models. Topics of interest include, but are not limited to:

• Empirical understanding of stakeholders' needs and goals in LLM evaluation and auditing
• Human-centered evaluation and auditing methods for LLMs
• Tools, processes, and guidelines for LLM evaluation and auditing
• Discussion of regulatory measures and public policies for LLM auditing
• Ethics in LLM evaluation and auditing

• Task allocation and workflow integration between human evaluators and AI agents
• Impact of hybrid human-AI approaches on vulnerability discovery
• Meta-evaluation frameworks for assessing trustworthiness of AI agents as auditing tools
• Methodologies for evaluating complex agent behaviors (multi-step reasoning, tool use, emergent patterns)
• Design patterns and safeguards for maintaining human oversight in automated evaluation
• Empirical studies of agent-assisted evaluation in practice

Submission Format: 2-6 pages ACM double-column, excluding references.

Submission Types: Position papers, full or in-progress empirical studies, literature reviews, system demos, method descriptions, or encore of published work (non-archival).

Review Process: Double-blind (except encore submissions). Papers will be selected based on the quality of the submission and diversity of perspectives to allow for a meaningful exchange of knowledge between a broad range of stakeholders.

Templates: [Word] [LaTeX] [Overleaf]

Notes:

• We encourage authors who submit also to help with the review process.
• For an encore submission, you do not need to anonymize the submission. Encore submissions will go through a jury review process.
• Please use \documentclass[sigconf,anonymous]{acmart} for submission.
• Please be aware of OpenReview's moderation policy for newly created profiles: new profiles created without an institutional email will go through a moderation process that can take up to two weeks, while new profiles created with an institutional email will be activated automatically.

→ Submission Site (Coming Soon)