Human-in-the-Loop Evaluation

Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality control procedure. In many service systems, the primary evidence of performance quality is textual -- customer support transcripts, complaint narratives, compliance review reports -- rather than the scalar measurements assumed by classical optimization methods. Large language models (LLMs) can read such textual evidence and produce standardized quality scores, but these automated judges exhibit systematic biases that vary across alternatives and evaluation instances. Human expert review remains accurate but costly. We study how to identify the best service configuration with high confidence while minimizing expensive human audits, given that automated evaluation is cheap but biased. We formalize this as a sequential decision problem where a biased proxy score is observed for every evaluation, and a verified outcome can be acquired selectively at additional cost. We prove that LLM-only selection fails under arm-dependent bias, and that naive selective-audit estimators can be asymptotically biased. We develop an estimator combining proxy scores with inverse-propensity-weighted residuals and construct anytime-valid confidence sequences. Our algorithm, PP-LUCB, jointly decides which alternatives to evaluate and whether to request human audits, concentrating reviews where the LLM judge is least reliable. We prove correctness and establish instance-dependent cost bounds showing near-optimal efficiency. On a customer support ticket classification task, our algorithm correctly identifies the best model in 40/40 trials while achieving 90% audit cost reduction.

Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate these methods. Many of the meta-evaluations estimate an evaluation quality's by comparing its assessments against human pairwise preferences. Prior work, however, suggests that human pairwise preference may be overly simplistic and can fail to capture nuances of expert expectations. We conduct a case study in meta-evaluation for long-form QA benchmarks using ScholarQA-CS2, a benchmark designed for assessing retrieval-augmented deep-research QA in the scientific domain. We comprehensively validate the benchmark through human pairwise preference judgments, then critically examine the strengths, weaknesses, and confounders of this approach. We show that pairwise preference rankings are best suited for system-level evaluation, while explicit metric-wise annotations and expert annotators are critical for reliable metric-level assessment, with subjectivity remaining a key challenge. Based on our findings, we offer practical guidelines for designing future meta-evaluations that better align evaluation methods, annotator expertise, and reporting practices. By surfacing these methodological challenges, we aim to advance evaluation standards for deep-research systems.

Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception. Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences. This challenge is further exacerbated by the ill-posed nature of IVIF, which severely limits its effectiveness in human perceptual environments such as security surveillance and driver assistance systems. To address these limitations, we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion. To address the lack of human-centric evaluation metrics and data, we introduce the first large-scale human feedback dataset for IVIF, containing multidimensional subjective scores and artifact annotations, and enriched by a fine-tuned large language model with expert review. Based on this dataset, we design a domain-specific reward function and train a reward model to quantify perceptual quality. Guided by this reward, we fine-tune the fusion network through Group Relative Policy Optimization, achieving state-of-the-art performance that better aligns fused images with human aesthetics. Code is available at https://github.com/ALKA-Wind/EVAFusion.

Human evaluations play a central role in training and assessing AI models, yet these data are rarely treated as measurements subject to systematic error. This paper integrates psychometric rater models into the AI pipeline to improve the reliability and validity of conclusions drawn from human judgments. The paper reviews common rater effects, severity and centrality, that distort observed ratings, and demonstrates how item response theory rater models, particularly the multi-faceted Rasch model, can separate true output quality from rater behavior. Using the OpenAI summarization dataset as an empirical example, we show how adjusting for rater severity produces corrected estimates of summary quality and provides diagnostic insight into rater performance. Incorporating psychometric modeling into human-in-the-loop evaluation offers more principled and transparent use of human data, enabling developers to make decisions based on adjusted scores rather than raw, error-prone ratings. This perspective highlights a path toward more robust, interpretable, and construct-aligned practices for AI development and evaluation.

Sustainability or ESG rating agencies use company disclosures and external data to produce scores or ratings that assess the environmental, social, and governance performance of a company. However, sustainability ratings across agencies for a single company vary widely, limiting their comparability, credibility, and relevance to decision-making. To harmonize the rating results, we propose adopting a universal human-AI collaboration framework to generate trustworthy benchmark datasets for evaluating sustainability rating methodologies. The framework comprises two complementary parts: STRIDE (Sustainability Trust Rating & Integrity Data Equation) provides principled criteria and a scoring system that guide the construction of firm-level benchmark datasets using large language models (LLMs), and SR-Delta, a discrepancy-analysis procedural framework that surfaces insights for potential adjustments. The framework enables scalable and comparable assessment of sustainability rating methodologies. We call on the broader AI community to adopt AI-powered approaches to strengthen and advance sustainability rating methodologies that support and enforce urgent sustainability agendas.

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a Computer User Agent, we investigate the utility of basic action traces for verification, explore three alternatives via design probes, and test a novel interface's impact on error finding in question-answering tasks. As expected, we find that current practices are cumbersome, limiting their efficacy. Conversely, our proposed design reduced the time participants spent finding errors. However, although participants reported higher levels of confidence in their decisions, their final accuracy was not meaningfully improved. To this end, our study surfaces challenges for human verification of agentic systems, including managing built-in assumptions, users' subjective and changing correctness criteria, and the shortcomings, yet importance, of communicating the agent's process.

Large Language Models (LLMs) are increasingly developed for use in complex professional domains, yet little is known about how teams design and evaluate these systems in practice. This paper examines the challenges and trade-offs in LLM development through a 12-week ethnographic study of a team building a pedagogical chatbot. The researcher observed design and evaluation activities and conducted interviews with both developers and domain experts. Analysis revealed four key practices: creating workarounds for data collection, turning to augmentation when expert input was limited, co-developing evaluation criteria with experts, and adopting hybrid expert-developer-LLM evaluation strategies. These practices show how teams made strategic decisions under constraints and demonstrate the central role of domain expertise in shaping the system. Challenges included expert motivation and trust, difficulties structuring participatory design, and questions around ownership and integration of expert knowledge. We propose design opportunities for future LLM development workflows that emphasize AI literacy, transparent consent, and frameworks recognizing evolving expert roles.

Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control.

Fact-checking systems must be scalable and epistemically trustworthy. We introduce Althea, a retrieval-augmented system for user-driven claim evaluation that matches standard pipelines on AVeriTeC while improving supported/refuted discrimination. A longitudinal survey experiment (N=961) treats a ten-day follow-up as a fading test: after modeling a verification procedure, we remove the system and ask whether users reproduce it unaided, testing metalearning rather than one-time accuracy. We compare two AI-assisted treatments, Exploratory (guided reasoning) and Summary (synthesized verdicts), against two baselines, unrelated news and Self-search. The treatments yield the strongest immediate accuracy and confidence gains but do not survive the fading test: on unseen claims they perform no better than news, while Self-search, with no procedure to fade, retains a large advantage. This reveals a factchecking-metalearning tradeoff: conditions that most improve immediate accuracy are least likely to produce metalearning, cautioning against treating AI-delivered verdicts as a source of durable literacy gains.

Reliable evaluation of large language models (LLMs) is critical as their deployment rapidly expands, particularly in high-stakes domains such as business and finance. The LLM-as-a-Judge framework, which uses prompted LLMs to evaluate response quality, is appealing due to its scalability, low cost, and strong correlations with human stylistic preferences. However, it remains unclear how accurately these methods can assess response quality in domains where correctness matters more than style. To address this gap, we introduce the Business and Finance Fundamentals Benchmark (BFF-Bench), a dataset of 160 challenging questions and long-form responses authored by financial professionals. These experts subsequently evaluated the correctness of 1,200 responses generated by a diverse set of LLMs on both BFF-Bench and a challenging subset of MT-Bench. With this expert-annotated dataset of judgments (VERDICTS), we analyze the agreement between a suite of automated grading methods and human experts. While we observe that LLM Judges are more reliable than other grading methods, our findings reveal a clear pattern in LLM Judge performance: when not provided with a correct reference, judges show high agreement with human experts only on questions the judges were able to correctly answer themselves. We demonstrate that providing the judges with expert-written references largely mitigates this issue, highlighting the limits of using LLM-as-a-Judge without any form of human verification.