Human-in-the-Loop Evaluation

Follow this topic Ask about this topic

This field examines how people evaluate AI outputs and collaborate with AI during testing and deployment, including whether systems are accurate, useful, safe, and appropriately trusted. Common approaches include expert rubrics and pairwise preferences, user studies and interaction traces, human-validated benchmarks, and LLM judges calibrated against human ratings, with uncertain or disputed cases escalated for review. Researchers also study how to allocate limited review effort, model annotator disagreement, and measure effects on human decisions and learning over time. The central tension is scaling evaluation with automated judges and simulations without losing expert context or mistaking agreement, confidence, or benchmark scores for real-world quality.

Latest papers

160 papers19 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Apr 30, 2026

End-to-End Evaluation and Governance of an EHR-Embedded AI Agent for Clinicians

Clinical AI systems require not just point-in-time evaluation but continuous governance: the ongoing practice of monitoring, evaluating, iterating, and re-evaluating performance throughout deployment. We present an end-to-end framework of governance that integrates rubric validation, live deployment feedback, technical performance monitoring, and cost tracking, with controlled experimentation gating system changes before deployment. Applied to Hyperscribe, an EHR-embedded agent that converts ambient audio into structured chart updates, twenty clinicians authored 1,646 validated rubrics across 823 cases. Seven Hyperscribe versions were evaluated through controlled experiments, with median scores improving from 84% to 95%. Analysis of 107 live feedback entries over three months showed feedback composition shifting from 79% error reports and 14% positive observations to 30% errors and 45% positive observations as engineering interventions resolved failures. Median processing time per audio segment was 8.1 seconds with a 99.6% effective completion rate after retry mechanisms absorbed transient model errors. These results demonstrate that continuous, multi-channel governance of deployed clinical AI is both achievable and effective.

Aaryan Shah, Andrew Hines, Alexia Downs +6

1Canvas Medical, San Francisco, CA, USA · Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · 3XPC (X Primary Care) +2

Healthcare AI Agent Evaluation Human-in-the-Loop Evaluation AI Agent Monitoring AI Agent Governance Electronic Health Records

Apr 29, 2026

Human-in-the-Loop Benchmarking of Heterogeneous LLMs for Automated Competency Assessment in Secondary Level Mathematics

As Competency-Based Education (CBE) is gaining traction around the world, the shift from marks-based assessment to qualitative competency mapping is a manual challenge for educators. This paper tackles the bottleneck issue by suggesting a "Human-in-the-Loop" benchmarking framework to assess the effectiveness of multiple LLMs in automating secondary-level mathematics assessment. Based on the Grade 10 Optional Mathematics curriculum in Nepal, we created a multi-dimensional rubric for four topics and four cross-cutting competencies: Comprehension, Knowledge, Operational Fluency, and Behavior and Correlation. The multi-provider ensemble, consisted of open-weight models -- Eagle (Llama 3.1-8B) and Orion (Llama 3.3-70B) -- and proprietary frontier models Nova (Gemini 2.5 Flash) and Lyra (Gemini 3 Pro), was benchmarked against a ground truth defined by two senior mathematics faculty members (kappa_w = 0.8652). The findings show a marked "Architecture-compatibility gap". Although the Gemini-based Mixture-of-Experts (Sparse MoE) models achieved "Fair Agreement" (kappa_w ~ 0.38), the larger Orion (70B) model exhibited "No Agreement" (kappa_w = -0.0261), suggesting that architectural compliance with instruction constraints outweighs the scale of raw parameters in rubric-constrained tasks. We conclude that while LLMs are not yet suitable for autonomous certification, they provide high-value assistive support for preliminary evidence extraction within a "Human-in-the-Loop" framework.

Jatin Bhusal, Nancy Mahatha, Aayush Acharya +1

Research and Incubation Center (RAIN), Sunway College Kathmandu

LLM Evaluation Educational Assessment Human-in-the-Loop Evaluation Rubric-Based Evaluation Automated Grading

Apr 27, 2026

Understanding the Limits of Automated Evaluation for Code Review Bots in Practice

Automated code review (ACR) bots are increasingly used in industrial software development to assist developers during pull request (PR) review. As adoption grows, a key challenge is how to evaluate the usefulness of bot-generated comments reliably and at scale. In practice, such evaluation often relies on developer actions and annotations that are shaped by contextual and organizational factors, complicating their use as objective ground truth. We examine the feasibility and limitations of automating the evaluation of LLM-powered ACR bots in an industrial setting. We analyze an industrial dataset from Beko comprising 2,604 bot-generated PR comments, each labeled by software engineers as fixed/wontFix. Two automated evaluation approaches, G-Eval and an LLM-as-a-Judge pipeline, are applied using both binary decisions and a 0-4 Likert-scale formulation, enabling a controlled comparison against developer-provided labels. Across Gemini-2.5-pro, GPT-4.1-mini, and GPT-5.2, both evaluation strategies achieve only moderate alignment with human labels. Agreement ratios range from approximately 0.44 to 0.62, with noticeable variation across models and between binary and Likert-scale formulations, indicating sensitivity to both model choice and evaluation design. Our findings highlight practical limitations in fully automating the evaluation of ACR bot comments in industrial contexts. Developer actions such as resolving or ignoring comments reflect not only comment quality, but also contextual constraints, prioritization decisions, and workflow dynamics that are difficult to capture through static artifacts. Insights from a follow-up interview with a software engineering director further corroborate that developer labeling behavior is strongly influenced by workflow pressures and organizational constraints, reinforcing the challenges of treating such signals as objective ground truth.

Veli Karakaya, Utku Boran Torun, Baykal Mehmet Uçar +1

Bilkent University Ankara, Turkey · Beko İstanbul, Turkey

LLM-as-a-Judge Human-in-the-Loop Evaluation Automated Code Review Automated Evaluation

Apr 27, 2026

Multi-Dimensional Evaluation of Sustainable City Trips with LLM-as-a-Judge and Human-in-the-Loop

Evaluating nuanced conversational travel recommendations is challenging when human annotations are costly and standard metrics ignore stakeholder-centric goals. We study LLMs-as-Judges for sustainable city-trip lists across four dimensions -- relevance, diversity, sustainability, and popularity balance, and propose a three-phase calibration framework: (1) baseline judging with multiple LLMs, (2) expert evaluation to identify systematic misalignment, and (3) dimension-specific calibration via rules and few-shot examples. Across two recommendation settings, we observe model-specific biases and high dimension-level variance, even when judges agree on overall rankings. Calibration clarifies reasoning per dimension but exposes divergent interpretations of sustainability, highlighting the need for transparent, bias-aware LLM evaluation. Prompts and code are released for reproducibility: https://github.com/ashmibanerjee/trs-llm-calibration.

Ashmi Banerjee, Adithi Satish, Wolfgang Wörndl +1

Technical University of Munich Munich, Germany · Polytechnic University of Bari Bari, Italy

LLM Evaluation LLM-as-a-Judge Human-in-the-Loop Evaluation Language Model Bias Evaluation Recommender Systems

Apr 24, 2026

Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented, evaluation remains reliant on quantitative proxies whose alignment with human utility is unverified. In this work, we use a unified amortized framework to isolate semantic differences between eight Shapley variants under the low-latency constraints of operational risk workflows. We conduct a large-scale empirical evaluation across four risk datasets and a realistic fraud-detection environment involving professional analysts and 3,735 case reviews. Our results reveal a fundamental misalignment: standard quantitative metrics, such as sparsity and faithfulness, are decoupled from human-perceived clarity and decision utility. Furthermore, while no formulation improved objective analyst performance, explanations consistently increased decision confidence, signaling a critical risk of automation bias in high-stakes settings. These findings suggest that current evaluation proxies are insufficient for predicting downstream human impact, and we provide evidence-based guidance for selecting formulations and metrics in operational decision systems.

Inês Oliveira e Silva, Sérgio Jesus, Iker Perez +4

University of Porto, Feedzai · Feedzai · University of Porto

Human-in-the-Loop Evaluation Shapley Value Attribution Human-AI Decision Making Explainability Evaluation

Apr 23, 2026

Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards

LLM leaderboards are widely used to compare models and guide deployment decisions. However, leaderboard rankings are shaped by evaluation priorities set by benchmark designers, rather than by the diverse goals and constraints of actual users and organizations. A single aggregate score often obscures how models behave across different prompt types and compositions. In this work, we conduct an in-depth analysis of the dataset used in the LMArena (formerly Chatbot Arena) benchmark and investigate this evaluation challenge by designing an interactive visualization interface as a design probe. Our analysis reveals that the dataset is heavily skewed toward certain topics, that model rankings vary across prompt slices, and that preference-based judgments are used in ways that blur their intended scope. Building on this analysis, we introduce a visualization interface that allows users to define their own evaluation priorities by selecting and weighting prompt slices and to explore how rankings change accordingly. A qualitative study suggests that this interactive approach improves transparency and supports more context-specific model evaluation, pointing toward alternative ways to design and use LLM leaderboards.

Minji Jung, Minjae Lee, Yejin Kim +2

Yonsei University, South Korea

LLM Evaluation Human-in-the-Loop Evaluation

Apr 20, 2026

CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks

AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency and generating economic value, this paradigm remains largely absent from occupational task evaluation, hindered by the difficulty of gathering real human data and accounting for inter-human variability. We introduce CollabSkill, a framework for evaluating human-agent collaboration on real-world occupational tasks. CollabSkill pairs real human workers with AI agents on tasks matched to their occupational background, collecting data that capture the complexity of economically valuable tasks and the usage patterns of real workers. To account for inter-human variability, CollabSkill employs a Bayesian skill rating system to disentangle and quantify the skill contributions of both humans and AI agents. Drawing on over 1,500 prompts from 386 working sessions contributed by 93 human workers, our analysis yields insights on two fronts: on the agent side, rankings on CollabSkill diverge meaningfully from those of existing fully autonomous benchmarks where Codex leads, with Claude Code ranking first; on the human side, CollabSkill reveals that practical experience emerges as the primary driver of collaboration skill, with hands-on collaboration meaningfully shifting workers' AI literacy. Together, we hope CollabSkill enables the community to invest in systematic evaluation of human-agent collaboration and spurs development efforts aimed at building AI agents that genuinely augment human workers.

Yijia Shao, Zora Zhiruo Wang, Neel Ahuja +3

Stanford University · Carnegie Mellon University · University of Rochester +1

AI Agent Evaluation Human-in-the-Loop Evaluation Human-AI Collaboration AI and Labor

Apr 16, 2026

AI-Assisted Requirements Engineering: An Empirical Evaluation Relative to Expert Judgment

Artificial Intelligence is increasingly introduced into systems engineering activities, particularly within requirements engineering, where quality assessment and validation remain heavily dependent on expert judgment. While recent AI tools demonstrate promising capabilities in analyzing and generating requirements, their role within formal systems engineering processes-and their alignment with established INCOSE criteria-remains insufficiently understood. This paper investigates the extent to which AI-based tools can support systems engineers in evaluating requirement quality, without replacing professional expertise. The research adopts a structured systems engineering methodology to compare AI-assisted requirement evaluation with human expert assessment. A controlled study was conducted in which system requirements were evaluated against established INCOSE ``good requirement'' criteria by both experienced systems engineers and an AI-based assessment tool. The evaluation focused on consistency, completeness, clarity, and testability, examining not only accuracy but also the decision logic underlying each assessment. Results indicate that AI tools can provide consistent and rapid preliminary assessments, particularly for syntactic and structural quality attributes. However, expert judgment remains essential for contextual interpretation, ambiguity resolution, and trade-off reasoning. Rather than positioning AI as a replacement for systems engineers, the findings support its role as a decision-support mechanism within the RE lifecycle. From a systems engineering perspective, this study contributes empirical evidence on how AI can be integrated into RE workflows while preserving traceability, accountability, and engineering consistency.

Oz Levy, Ilya Dikman, Natan Levy +1

Faculty of Industrial Engineering and Technology Management, Holon Institute of Technology (HIT) Holon, Israel · School of Computer Science and Engineering Hebrew University Jerusalem (HUJI) Jerusalem, Israel

Requirements Engineering Human-in-the-Loop Evaluation Automated Evaluation

Apr 12, 2026

RuleEdit: Failure-Guided Human-AI Model Editing with Prospective Impact Preview

Despite the promise of AI to assist complex decisions, practitioners still lack ways to detect likely failures and inspect the consequences of model edits before committing them. We present RuleEdit, an interactive, rule-guided human-AI model editing system that (i) surfaces likely failures through interpretable mismatch signals from rule tables and (ii) supports user-authored rule feedback with prospective previews of projected performance changes and embedding shifts. We instantiate RuleEdit in stroke rehabilitation assessment and evaluate it with health professionals and students. Rule-guided failure detection significantly increased Human + AI performance by 14.16% (

p<0.001

) while improving rejection of incorrect AI and reducing both over- and under- reliance as well as ChangedToWrong decisions. In addition, presenting prospective embedding previews improved participants' feedback for model adaptation, increasing post-update local performance gains from 11.50% to 36.38% after incorporating users' rule-based feedback (

p<0.001

). Our findings show that mismatch-based failure cues and prospective impact previews can support failure-aware human-AI model editing, while also revealing a local-global tradeoff: edits that help a specific case can degrade performance when transferred globally. We discuss implications of designing failure-aware and controllable human-AI systems.

Min Hun Lee, Justin Yu Feng Teo

Singapore Management University, Singapore

Model Editing Human-AI Decision Making Human-in-the-Loop Evaluation

Apr 10, 2026

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgment: knowing when to act autonomously and when to ask for help. Current benchmarks are blind to this failure mode. They supply unambiguous detailed instructions and solely reward execution correctness, so an agent that makes a lucky guess for a missing requirement will score identically to one that would have asked to be certain. We present HiL-Bench (Human-in-the-Loop Benchmark) to measure this selective escalation skill. Each task contains human-validated blockers (missing information, ambiguous requests, contradictory information) that surface only through progressive exploration, not upfront inspection. Our core metric, Ask-F1, the harmonic mean of question precision and blocker recall, captures the tension between over-asking and silent guessing; its structure architecturally prevents gaming through question spam. Evaluation across SWE and text-to-SQL domains reveals a large universal judgment gap: no frontier model recovers more than a fraction of its full-information performance when deciding whether to ask. Failure analysis identifies three key help-seeking patterns: overconfident wrong beliefs with no gap detection; high uncertainty detection yet persistent errors; broad, imprecise escalation without self-correction. These consistent patterns confirm poor help-seeking is a model-level flaw, not task-specific. RL training on shaped Ask-F1 reward shows judgment is trainable: a 32B model improves both help-seeking quality and task pass rate, with gains that transfer across domains. The model does not learn domain-specific heuristics for when to ask; it learns to detect unresolvable uncertainty and act on it.

Tu Trinh, Mohamed Elfeki, Guangze Luo +9

LLM Agents AI Agent Benchmarks Human-in-the-Loop Evaluation Software Engineering Agents

Apr 10, 2026

MuTSE: A Human-in-the-Loop Multi-use Text Simplification Evaluator

As Large Language Models (LLMs) become increasingly prevalent in text simplification, systematically evaluating their outputs across diverse prompting strategies and architectures remains a critical methodological challenge in both NLP research and Intelligent Tutoring Systems (ITS). Developing robust prompts is often hindered by the absence of structured, visual frameworks for comparative text analysis. While researchers typically rely on static computational scripts, educators are constrained to standard conversational interfaces -- neither paradigm supports systematic multi-dimensional evaluation of prompt-model permutations. To address these limitations, we introduce MuTSE\footnote{The project code and the demo have been made available for peer review at the following anonymized URL. https://osf.io/njs43/overview?view_only=4b4655789f484110a942ebb7788cdf2a, an interactive human-in-the-loop web application designed to streamline the evaluation of LLM-generated text simplifications across arbitrary CEFR proficiency targets. The system supports concurrent execution of

P \times M

prompt-model permutations, generating a comprehensive comparison matrix in real-time. By integrating a novel tiered semantic alignment engine augmented with a linearity bias heuristic (

λ

), MuTSE visually maps source sentences to their simplified counterparts, reducing the cognitive load associated with qualitative analysis and enabling reproducible, structured annotation for downstream NLP dataset construction.

Rares-Alexandru Roscan, Gabriel Petre1, Adrian-Marius Dumitran +1

University of Bucharest, Faculty of Mathematics and Computer Science, Academiei 14, 010014, Bucharest, Romania · Cu Drag si Sport SRL, Bucharest, Romania · Softbinator Technologies, Bucharest, Romania +1

Semantic Alignment Text Simplification Language Model Generation Evaluation Human-in-the-Loop Evaluation

Apr 9, 2026

Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study

In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisation, it remains unclear to what extent ``human-in-the-loop'' oversight is required to sustain performance uplift over time. This paper presents a longitudinal case study analysing a real-world consumer application that leverages agentic infrastructure to personalise marketing messaging for a large-scale user base over an 11-month period. We compare two distinct periods: an active phase where marketers directly curated content, audiences, and strategies -- followed immediately by a passive phase where agents operated autonomously from a fixed library of components. Our results demonstrate that whilst active human management generates the highest relative lift in engagement metrics, the autonomous agents successfully sustained a positive lift during the passive period. These findings suggest a symbiotic model where human intervention drives strategic initialisation and discovery, yet autonomous agents can ensure the scalable retention and preservation of performance gains.

Olivier Jeunen, Eleanor Hanna, Schaun Wheeler

aampe Antwerp, Belgium · aampe Raleigh, NC, USA · aampe Cary, NC, USA

Human-in-the-Loop Evaluation Long-Horizon Agent Evaluation

Apr 9, 2026

"Why This Avoidance Maneuver?" Contrastive Explanations in Human-Supervised Maritime Autonomous Navigation

Automated maritime collision avoidance will rely on human supervision for the foreseeable future. This necessitates transparency into how the system perceives a scenario and plans a maneuver. However, the causal logic behind avoidance maneuvers is often complex and difficult to convey to a navigator. This paper explores how to explain these factors in a selective, understandable manner for supervisors with a nautical background. We propose a method for generating contrastive explanations, which provide human-centric insights by comparing a system's proposed solution against relevant alternatives. To evaluate this, we developed a framework that uses visual and textual cues to highlight key objectives from a state-of-the-art collision avoidance system. An exploratory user study with four experienced marine officers suggests that contrastive explanations support the understanding of the system's objectives. However, our findings also reveal that while these explanations are highly valuable in complex multi-vessel encounters, they can increase cognitive workload, suggesting that future maritime interfaces may benefit most from demand-driven or scenario-specific explanation strategies.

Joel Jose, Andreas Madsen, Andreas Brandsæter +2

Department of ICT and Natural Sciences, Norwegian University of Science and Technology (NTNU), Ålesund, Norway. · Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), Ålesund, Norway. · Department of Science and Mathematics, Volda University College (HVO), Volda, Norway. +1

Explainable Motion Planning Counterfactual Explanations Robot Navigation Collision Avoidance Human-in-the-Loop Evaluation

Apr 3, 2026

Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization

Optimization is as much about modeling the right problem as solving it. Identifying the right objectives, constraints, and trade-offs demands extensive interaction between researchers and stakeholders. Large language models can empower decision-makers with optimization capabilities through interactive optimization agents that can propose, interpret and refine solutions. However, it is fundamentally harder to evaluate a conversation-based interaction than traditional one-shot approaches. This paper proposes a scalable and replicable methodology for evaluating optimization agents through conversations. We build LLM-powered decision agents that role-play diverse stakeholders, each governed by an internal utility function but communicating like a real decision-maker. We generate thousands of conversations in a school scheduling case study. Results show that one-shot evaluation is severely limiting: the same optimization agent converges to much higher-quality solutions through conversations. Then, this paper uses this methodology to demonstrate that tailored optimization agents, endowed with domain-specific prompts and structured tools, can lead to significant improvements in solution quality in fewer interactions, as compared to general-purpose chatbots. These findings provide evidence of the benefits of emerging solutions at the AI-optimization interface to expand the reach of optimization technologies in practice. They also uncover the impact of operations research expertise to facilitate interactive deployments through the design of effective and reliable optimization agents.

Joshua Drossman, Alexandre Jacquillat, Sébastien Martin

Operations Research Center and Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA. · Kellogg School of Management, Northwestern University, Evanston, IL

LLM Agent Evaluation Human-in-the-Loop Evaluation

Mar 31, 2026

Semantic Interaction for Narrative Map Sensemaking: An Insight-based Evaluation

Semantic interaction (SI) enables analysts to incorporate their cognitive processes into AI models through direct manipulation of visualizations. While SI frameworks for narrative extraction have been proposed, empirical evaluations of their effectiveness remain limited. This paper presents a user study that evaluates SI for narrative map sensemaking, involving 33 participants under three conditions: a timeline baseline, a basic narrative map, and an interactive narrative map with SI capabilities. The results show that the map-based prototypes yielded more insights than the timeline baseline, with the SI-enabled condition reaching statistical significance and the basic map condition trending in the same direction. The SI-enabled condition showed the highest mean performance; differences between the map conditions were not statistically significant but showed large effect sizes (d > 0.8), suggesting that the study was underpowered to detect them. Qualitative analysis identified two distinct SI approaches-corrective and additive-that enable analysts to impose quality judgments and organizational structure on extracted narratives. We also find that SI users achieved comparable exploration breadth with less parameter manipulation, suggesting that SI serves as an alternative pathway for model refinement. This work provides empirical evidence that map-based representations outperform timelines for narrative sensemaking, along with qualitative insights into how analysts use SI for narrative refinement.

Brian Felipe Keith-Norambuena, Fausto German, Eric Krokos +2

Universidad Católica del Norte, Av. Angamos 0610, Antofagasta, 1270709, Chile · Virginia Tech, 620 Drillfield Drive, Blacksburg, VA, 24061, USA · U.S. Government, Washington, D.C. 20500, USA

Visual Analytics Human-in-the-Loop Evaluation

Mar 28, 2026

Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric "black boxes," producing fluent rationales that overlook localized framing. Preliminary evidence from the multilingual Information Disorder (InDor) corpus suggests that existing models struggle to explain manipulated news consistently across communities. To address this gap, this ongoing study proposes a Hybrid Intelligence Loop, a human-in-the-loop (HITL) framework that grounds model assessment in human-written rationales from native-speaking annotators. The approach moves beyond static target-language few-shot prompting by pairing English task instructions with dynamically retrieved target-language exemplars drawn from filtered InDor annotations through In-Context Learning (ICL). In the initial pilot, the Exemplar Bank is seeded from these filtered annotations and used to compare static and adaptive prompting on Farsi and Italian news. The study evaluates span and severity prediction, the quality and cultural appropriateness of generated rationales, and model alignment across evaluator groups, providing a testbed for culturally grounded explainable AI.

Maziar Kianimoghadam Jouneghani

University of Turin

Cross-Cultural Language Model Evaluation Faithfulness of Language Model Explanations Human-in-the-Loop Evaluation

Mar 27, 2026

User Involvement in Robotic Wheelchair Development: A Decade of Limited Progress

Robotic wheelchairs (RWs) offer significant potential to enhance autonomy and participation for people with mobility impairments, yet many systems have failed to achieve sustained real-world adoption. This narrative literature review examined the extent and quality of end-user involvement in RW design, development, and evaluation over the past decade (2015--2025), assessed against core principles shared by major user-involvement approaches (e.g., user-/human-centered design, participatory/co-design, and inclusive design). The findings indicate that user involvement remains limited and is predominantly concentrated in late-stage evaluation rather than in early requirements definition or iterative co-design. Of the 399 records screened, only 23 studies (about 6%) met the inclusion criteria of verifiable end-user involvement, and many relied on small samples, often around ten participants, with limited justification for sample size selection, proxy users, laboratory-based validation, and non-standardized feedback methods. Research teams were largely engineering-dominated (about 89%) and geographically concentrated in high-income countries. Despite strong evidence that sustained user engagement improves usability and adoption in assistive technology, its systematic implementation in RW research remains rare. Advancing the field requires embedding participatory methodologies throughout the design lifecycle and addressing systemic barriers that constrain meaningful user involvement.

Mario Andres Chavarria, Santiago Price Torrendell, Aude Billard +7

Geneva School of Health Science, University of Applied Sciences and Arts Western Switzerland, Geneva, Switzerland · Institute Of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan · Learning Algorithms and Systems Laboratory, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland +7

Participatory Design Assistive Robotics Human-in-the-Loop Evaluation

Mar 24, 2026

Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation

During human motor skill training and physical rehabilitation, there is an inherent trade-off between task difficulty and user performance. Characterizing this trade-off is crucial for evaluating user performance, designing assist-as-needed (AAN) protocols, and assessing the efficacy of training protocols. In this study, we propose a novel human-in-the-loop (HiL) Pareto optimization approach to characterize the trade-off between task performance and the perceived challenge level of motor learning or rehabilitation tasks. We adapt Bayesian multi-criteria optimization to systematically and efficiently perform HiL Pareto characterizations. Our HiL optimization employs a hybrid model that measures performance with a quantitative metric, while the perceived challenge level is captured with a qualitative metric. We demonstrate the feasibility of the proposed HiL Pareto characterization through a user study. Furthermore, we present the utility of the framework through three use cases in the context of a manual skill training task with haptic feedback. First, we demonstrate how the characterized trade-off can be used to design a sample AAN training protocol for a motor learning task and to evaluate the group-level efficacy of the proposed AAN protocol relative to a baseline adaptive assistance protocol. Second, we demonstrate that individual-level comparisons of the trade-offs characterized before and after the training session enable fair evaluation of training progress under different assistance levels. This evaluation method is more general than standard performance evaluations, as it can provide insights even when users cannot perform the task without assistance. Third, we show that the characterized trade-offs also enable fair performance comparisons among different users, as they capture the best possible performance of each user under all feasible assistance levels.

Harun Tolasa, Volkan Patoglu

the Faculty of Engineering and Natural Sciences at Sabanci University, Istanbul, Turkiye.

Human-in-the-Loop Evaluation Pareto Optimization Human-in-the-Loop AI

Mar 24, 2026

LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks

Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct answer. In contrast, real-world enterprise work is often subjective and context-dependent: success hinges on organizational goals, user intent, and the quality of intermediate artifacts produced across long, multi-tool workflows. We introduce LH-Bench, a three-pillar evaluation design that moves beyond binary correctness to score autonomous, long-horizon execution on subjective enterprise tasks. The pillars are: (i) expert-grounded rubrics that give LLM judges the domain context needed to score subjective work, (ii) curated ground-truth artifacts that enable stepwise reward signals (e.g., chapter-level annotation for content tasks), and (iii) pairwise human preference evaluation for convergent validation. We show that domain-authored rubrics provide substantially more reliable evaluation signals than LLM-authored rubrics (kappa = 0.60 vs. 0.46), and that human preference judgments confirm the same top-tier separation (p < 0.05), evidence that expert-grounded evaluation can scale without sacrificing reliability. We release public datasets and report results on two environments: Figma-to-code (33 real .fig tasks against the Figma API via MCP) and Programmatic content (41 courses comprising 183 individually-evaluated chapters on a course platform serving 30+ daily users).

Abhishek Chandwani, Ishan Gupta

Metaphi Inc. USA

Long-Horizon Agent Evaluation AI Agent Benchmarks LLM-as-a-Judge Human-in-the-Loop Evaluation

Mar 19, 2026

From Accuracy to Readiness: Metrics and Benchmarks for Human-AI Decision-Making

Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively. Empirical evidence shows that many failures arise from miscalibrated reliance, including overuse when AI is wrong and underuse when it is helpful. This paper proposes a measurement framework for evaluating human-AI decision-making centered on team readiness. We introduce a four part taxonomy of evaluation metrics spanning outcomes, reliance behavior, safety signals, and learning over time, and connect these metrics to the Understand-Control-Improve (U-C-I) lifecycle of human-AI onboarding and collaboration. By operationalizing evaluation through interaction traces rather than model properties or self-reported trust, our framework enables deployment-relevant assessment of calibration, error recovery, and governance. We aim to support more comparable benchmarks and cumulative research on human-AI readiness, advancing safer and more accountable human-AI collaboration.

Min Hun Lee

Singapore Management University, Singapore

Human-AI Decision Making Human-AI Collaboration Human-in-the-Loop Evaluation

Mar 19, 2026

A Human-in/on-the-Loop Framework for Accessible Text Generation

Plain Language and Easy-to-Read formats in text simplification are essential for cognitive accessibility. Yet current automatic simplification and evaluation pipelines remain largely automated, metric-driven, and fail to reflect user comprehension or normative standards. This paper introduces a hybrid framework that explicitly integrates human participation into LLM-based accessible text generation. Human-in-the-Loop (HiTL) contributions guide adjustments during generation, while Human-on-the-Loop (HoTL) supervision ensures systematic post-generation review. Empirical evidence from user studies and annotated resources is operationalized into (i) checklists aligned with standards, (ii) Event-Condition-Action trigger rules for activating expert oversight, and (iii) accessibility Key Performance Indicators (KPIs). The framework shows how human-centered mechanisms can be encoded for evaluation and reused to provide structured feedback that improves model adaptation. By embedding the human role in both generation and supervision, it establishes a traceable, reproducible, and auditable process for creating and evaluating accessible texts. In doing so, it integrates explainability and ethical accountability as core design principles, contributing to more transparent and inclusive NLP systems.

Lourdes Moreno, Paloma Martínez

Universidad Carlos III de Madrid Av. Universidad, 30, Leganés, 28911, Spain

Text Simplification Human-in-the-Loop AI Text Generation Human-in-the-Loop Evaluation

Mar 18, 2026

Multisource human-in-the-loop digital twin testbed for connected and autonomous vehicles in mixed traffic flow

In the emerging mixed traffic environments, Connected and Autonomous Vehicles (CAVs) have to interact with surrounding human-driven vehicles (HDVs). This paper introduces MSH-MCCT (Multi-Source Human-in-the-Loop Mixed Cloud Control Testbed), a novel CAV testbed that captures complex interactions between various CAVs and HDVs. Utilizing the Mixed Digital Twin concept, which combines Mixed Reality with Digital Twin, MSH-MCCT integrates physical, virtual, and mixed platforms, along with multi-source control inputs. Bridged by the mixed platform, MSH-MCCT allows human drivers and CAV algorithms to operate both physical and virtual vehicles within multiple fields of view. Particularly, this testbed facilitates the coexistence and real-time interaction of physical and virtual CAVs & HDVs, significantly enhancing the experimental flexibility and scalability. Experiments on vehicle platooning in mixed traffic showcase the potential of MSH-MCCT to conduct CAV testing with multi-source real human drivers in the loop through driving simulators of diverse fidelity. The videos for the experiments are available at our project website: https://dongjh20.github.io/MSH-MCCT.

Jianghong Dong, Chunying Yang, Mengchi Cai +5

School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China. · Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI 48109, USA.

Intelligent Transportation Systems Autonomous Driving Simulation Digital Twins Human-in-the-Loop Evaluation

Mar 18, 2026

From Optimizable to Interactable: Mixed Digital Twin-Empowered Testing of Vehicle-Infrastructure Cooperation Systems

Sufficient testing under corner cases is critical for the long-term operation of vehicle-infrastructure cooperation systems (VICS). However, existing corner-case generation methods are primarily AI-driven, and VICS testing under corner cases is typically limited to simulation. In this paper, we introduce an L5 ''Interactable'' level to the VICS digital twin (VICS-DT) taxonomy, extending beyond the conventional L4 ''Optimizable'' level. We further propose an L5-level VICS testing framework, IMPACT (Interactive Mixed-digital-twin Paradigm for Advanced Cooperative vehicle-infrastructure Testing). By enabling direct human interactions with VICS entities, IMPACT incorporates highly uncertain and unpredictable human behaviors into the testing loop, naturally generating high-quality corner cases that complement AI-based methods. Furthermore, the mixedDT-enabled ''Physical-Virtual Action Interaction'' facilitates safe VICS testing under corner cases, incorporating real-world environments and entities rather than purely in simulation. Finally, we implement IMPACT on the I-VIT (Interactive Vehicle-Infrastructure Testbed), and experiments demonstrate its effectiveness. The experimental videos are available at our project website: https://dongjh20.github.io/IMPACT.

Jianghong Dong, Chunying Yang, Mengchi Cai +4

School of Vehicle and Mobility, Tsinghua University, 100084 Beijing, China

Intelligent Transportation Systems Digital Twins Autonomous Driving Safety Evaluation Autonomous Driving Scenario Generation Human-in-the-Loop Evaluation

Mar 14, 2026

When Should Humans Step In? Optimal Human Dispatching in AI-Assisted Decisions

AI systems increasingly assist decision making by producing cheap factor-level assessments of complex inputs, but these assessments can be biased or incomplete. We study selective human evaluation: given AI signals, which factors should be dispatched to human experts? We formulate this human--AI collaboration problem as a factor-level information-acquisition problem. Under squared loss, the optimal dispatching rule maximizes a contextual reward; under a linear model, this reward admits a closed-form decomposition into two interpretable terms: predictive relevance and residual uncertainty in the human evaluation after conditioning on the AI signal. We instantiate the framework on peer review, decomposing papers into ten aspects and evaluating up to 3,408 ICLR submissions across three LLMs and multiple regression heads. In this retrospective proxy, where human aspect signals are extracted from existing reviews, predictions that query three of the ten aspects under the optimal dispatching rules match the full ten-aspect human benchmark. The finding holds when the human signal comes from a single noisy reviewer, and across review years. These results position principled dispatching as a practical building block for scalable human--AI decision systems. We also discuss safeguards under which such a rule can serve as decision support that leaves the final decision with a human.

Lezhi Tan, Naomi Sagan, Lihua Lei +1

Stanford University, USA

AI-Assisted Decision Making Human-AI Collaboration Human-in-the-Loop Evaluation

Mar 13, 2026

Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments

Providing timely and individualised feedback on handwritten student work is highly beneficial for learning but difficult to achieve at scale. This challenge has become more pressing as generative AI undermines the reliability of take-home assessments, shifting emphasis toward supervised, in-class evaluation. We present a scalable, end-to-end workflow for LLM-assisted grading of short, pen-and-paper assessments. The workflow spans (1) constructing solution keys, (2) developing detailed rubric-style grading keys used to guide the LLM, and (3) a grading procedure that combines automated scanning and anonymisation, multi-pass LLM scoring, automated consistency checks, and mandatory human verification. We deploy the system in two undergraduate mathematics courses using six low-stakes in-class tests. Empirically, LLM assistance reduces grading time by approximately 23% while achieving agreement comparable to, and in several cases tighter than, fully manual grading. Occasional model errors occur but are effectively contained by the hybrid design. Overall, our results show that carefully embedded human-in-the-loop LLM grading can substantially reduce workload while maintaining fairness and accuracy.

Arne Vanhoyweghen, Vincent Holst, Melika Mobini +9

Data Analytics Lab, Vrije Universiteit Brussel, 1050 Brussel, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA

Automated Grading AI in Education Human-in-the-Loop Evaluation

Mar 13, 2026

Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback

As virtual try-on (VTON) systems become increasingly important in fashion e-commerce, there is a growing need for reliable reference-free evaluation methods, since ground-truth images of the same person wearing the target garment are typically unavailable in real-world scenarios. To address this challenge, we propose VTON-IQA, a reference-free framework for human-aligned image quality assessment without requiring ground-truth images. To model human perceptual judgments, we construct VTON-QBench, a large-scale human-annotated benchmark comprising 62,688 try-on images generated by 14 representative VTON models and 431,800 quality annotations collected from 13,838 qualified annotators. To the best of our knowledge, this is the largest dataset to date for human subjective evaluation in VTON. Extensive experiments show that VTON-IQA achieves reliable human-aligned image quality assessment. Moreover, we conduct a comprehensive benchmark evaluation of 14 representative VTON models using VTON-IQA.

Yuki Hirakawa, Takashi Wada, Ryotaro Shimizu +6

ZOZO Research · ZOZO Inc. · Keio University

Virtual Try-On Human-in-the-Loop Evaluation Image Quality Assessment

Mar 13, 2026

Human-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts

Integrating Large Language Models (LLMs) into business process management tools promises to democratize Business Process Model and Notation (BPMN) modeling for non-experts. While automated frameworks assess syntactic and semantic quality, they miss human factors like trust, usability, and professional alignment. We conducted a mixed-methods evaluation of our proposed solution, an LLM-powered BPMN copilot, with five process modeling experts using focus groups and standardized questionnaires. Our findings reveal a critical tension between acceptable perceived usability (mean CUQ score: 67.2/100) and notably lower trust (mean score: 48.8%), with reliability rated as the most critical concern (M=1.8/5). Furthermore, we identified output-quality issues, prompting difficulties, and a need for the LLM to ask more in-depth clarifying questions about the process. We envision five use cases ranging from domain-expert support to enterprise quality assurance. We demonstrate the necessity of human-centered evaluation complementing automated benchmarking for LLM modeling agents.

Chantale Lauer, Peter Pfeiffer, Nijat Mehdiyev

Saarland University, Saarbrücken, Saarland, Germany · German Research Institute for Artificial Intelligence, Saarbrücken, Saarland, Germany · 5Plus GmbH, Würzburg, Bavaria, Germany

Business Process Modeling LLM Agent Evaluation Trust in AI LLM Reliability Human-in-the-Loop Evaluation

Mar 12, 2026

Agreement Between Large Language Models, Human Reviewers, and Authors in Evaluating STROBE Checklists for Observational Studies in Rheumatology

Introduction: Evaluating compliance with the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement can be time-consuming and subjective. This study compares STROBE assessments from large language models (LLMs), a human reviewer panel, and the original manuscript authors in observational rheumatology research. Methods: Guided by the GRRAS and DEAL Pathway B frameworks, 17 rheumatology articles were independently assessed. Evaluations used the 22-item STROBE checklist, completed by the authors, a five-person human panel (ranging from junior to senior professionals), and two LLMs (ChatGPT-5.2, Gemini-3Pro). Items were grouped into Methodological Rigor and Presentation and Context domains. Inter-rater reliability was calculated using Gwet's Agreement Coefficient (AC1). Results: Overall agreement across all reviewers was 85.0% (AC1=0.826). Domain stratification showed almost perfect agreement for Presentation and Context (AC1=0.841) and substantial agreement for Methodological Rigor (AC1=0.803). Although LLMs achieved complete agreement (AC1=1.000) with all human reviewers on standard formatting elements, their agreement with human reviewers and authors declined on complex items. For example, regarding the item on loss to follow-up, the agreement between Gemini 3 Pro and the senior reviewer was AC1=-0.252, while the agreement with the authors was only fair. Additionally, ChatGPT-5.2 generally demonstrated higher agreement with human reviewers than Gemini-3Pro on specific methodological items. Conclusion: While LLMs show potential for basic STROBE screening, their lower agreement with human experts on complex methodological items likely reflects a reliance on surface-level information. Currently, these models appear more reliable for standardizing straightforward checks than for replacing expert human judgment in evaluating observational research.

Emre Bilgin, Ebru Ozturk, Meera Shah +6

Sakarya University, Faculty of Medicine, Department of Internal Medicine, Division of Rheumatology, Sakarya, Turkiye · Topiwala NaBonal Medical College and B.Y.L. Nair Hospital, Department of Rheumatology, , Mumbai, India · St Luke’s Medical Center (Global City), Philippines +9

LLM Evaluation Healthcare Human-in-the-Loop Evaluation

Mar 12, 2026

CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading

Scaling educational assessment with large language models requires not just accuracy, but the ability to recognize when predictions are trustworthy. Instruction-tuned models tend to be overconfident, and their reliability deteriorates as curricula evolve, making fully autonomous deployment unsafe in high-stakes settings. We introduce CHiL(L)Grader, the first automated grading framework that incorporates calibrated confidence estimation into a human-in-the-loop workflow. Using post-hoc temperature scaling, confidence-based selective prediction, and continual learning, CHiL(L)Grader automates only high-confidence predictions while routing uncertain cases to human graders, and adapts to evolving rubrics and unseen questions. Across three short-answer grading datasets, CHiL(L)Grader automatically scores 35-65% of responses at expert-level quality (QWK >= 0.80). A QWK gap of 0.347 between accepted and rejected predictions confirms the effectiveness of the confidence-based routing. Each correction cycle strengthens the model's grading capability as it learns from teacher feedback. These results show that uncertainty quantification is key for reliable AI-assisted grading.

Pranav Raikote, Korbinian Randl, Ioanna Miliou +2

Department of Computer and Systems Sciences, Stockholm University, 164 25 Kista, Sweden

Automated Grading AI in Education Human-in-the-Loop Evaluation Language Model Calibration

Mar 11, 2026

Mind the Sim2Real Gap in User Simulation for Agentic Tasks

As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, serving two roles: generating user turns and providing evaluation signals. Yet, these simulations are frequently assumed to be faithful to real human behaviors, often without rigorous verification. We formalize the Sim2Real gap in user simulation and present the first study running the full

τ

-bench protocol with real humans (451 participants, 165 tasks), benchmarking 31 LLM simulators across proprietary, open-source, and specialized families using the User-Sim Index (USI), a metric we introduce to quantify how well LLM simulators resemble real user interactive behaviors and feedback. Behaviorally, LLM simulators are excessively cooperative, stylistically uniform, and lack realistic frustration or ambiguity, creating an "easy mode" that inflates agent success rates above the human baseline. In evaluations, real humans provide nuanced judgments across eight quality dimensions while simulated users produce uniformly more positive feedback; rule-based rewards are failing to capture rich feedback signals generated by human users. Overall, higher general model capability does not necessarily yield more faithful user simulation. These findings highlight the importance of human validation when using LLM-based user simulators in the agent development cycle and motivate improved models for user simulation.

Xuhui Zhou, Weiwei Sun, Qianou Ma +8

Carnegie Mellon University, Language Technologies Institute

User Simulation Sim-to-Real Transfer LLM Agent Evaluation Human-in-the-Loop Evaluation