Building effective AI systems increasingly depends on writing high-quality task requirements, yet users often struggle to articulate the constraints, preferences, and edge cases that determine success. This problem is especially acute in AI development, where behavior is shaped not only by human expectations but also by data characteristics. We present AREAs-Lab, an interactive environment for AI-driven Requirement Elicitation for AI systems. In AREAs-Lab, an assistant iteratively refines an initially incomplete requirement by analyzing the underlying dataset and asking targeted clarification questions to uncover the user’s latent intent. To study this setting systematically, we construct a synthetic benchmark grounded in 16 public datasets spanning diverse domains and task types. Each benchmark instance includes a user profile, a complete reference requirement, and an intentionally underspecified version that serves as the assistant’s starting point. We further introduce an automated evaluation pipeline based on an AI-simulated user that reveals hidden information only when appropriately prompted, enabling scalable and reproducible assessment of interactive elicitation quality. AREAs-Lab provides a controlled testbed for studying how AI assistants can transform vague user goals into actionable requirements for AI systems.

LLM-as-a-Judge systems are increasingly employed for automated evaluation, yet remain susceptible to systematic biases that undermine their reliability. We demonstrate that the judge can effectively debias itself without additional training. We propose two lightweight strategies: bias-aware prompting, which explicitly alerts the judge to potential target biases prior to evaluation, and self-debiasing, in which the judge critiques the initial judgment for bias influence. To broaden the evaluation scope, we introduce three novel benchmarks—authority bias (fabricated citations), confidence bias (assertive phrasing), and formatting bias (structured presentation)—and evaluate across seven bias types in total. Across three frontier models, self-debiasing improves performance in 20 out of 21 model–bias combinations with gains up to 15 percentage points, while bias-aware prompting also yields consistent improvements. The recent fine-tuned external critic, however, does not generalize as reliably to the newly-introduced bias types (degradation observed in 5 out of 9 cases). Our findings demonstrate that prompting a judge to reason about bias, either preemptively or retrospectively, is a robust and generalizable approach for enhancing evaluation integrity.

Human-written references are typically treated as the upper-bound gold standard for fine-tuning and evaluation, but writing them is an inefficient use of subject-matter expert (SME) time. To best use limited SME attention, we apply psychometric standard-setting to discover acceptance criteria for GenAI applications. These acceptance boundaries are themselves useful for calibrating an LLM-as-a-judge, model tuning, and defensible production monitoring. We report a case study on summarization across two domains at a large US financial institution. While summarization is a classic GenAI use case, what counts as acceptable differs significantly across domains. 25 SMEs across three panels produced 2,500+ judgments and yielded calibrated thresholds in an estimated 10x less SME time than the standard playbook of writing golden reference (goldens) directly. In both domains, LLM-generated goldens are preferred over SME-written ones ~80% of the time. Limited SME attention is best used to judge candidate goldens rather than write them.

Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the ideal summary must satisfy a set of complex, multi-faceted requirements. While summarization has received immense attention in research, prior work has primarily utilized static datasets and benchmarks, a condition rare in practical scenarios where requirements inevitably evolve. In this work, we present an industry case study on developing an agentic system to summarize multi-party interactions. We share practical insights spanning the full development lifecycle to guide practitioners in building reliable, adaptable summarization systems, as well as to inform future research, covering: 1) robust methods for evaluation despite evolving requirements and task subjectivity, 2) component-wise optimization enabled by the task decomposition inherent in an agentic architecture, 3) the impact of upstream data bottlenecks, and 4) the realities of vendor lock-in due to the poor transferability of LLM prompts.

We propose a framework to modularize the training of neural language models that use diverse forms of context by eliminating the need to jointly train context and within-sentence encoders. Our approach, contextual universal embeddings (CUE), trains LMs on one type of contextual data and adapts to novel context types. The model consists of a pretrained neural sentence LM, a BERT-based contextual encoder, and a masked transfomer decoder that estimates LM probabilities using sentence-internal and contextual evidence. When contextually annotated data is unavailable, our model learns to combine contextual and sentence-internal information using noisy oracle unigram embeddings as a proxy. Real context data can be introduced later and used to adapt a small number of parameters that map contextual data into the decoder’s embedding space. We validate the CUE framework on a NYTimes text corpus with multiple metadata types, for which the LM perplexity can be lowered from 36.6 to 27.4 by conditioning on context. Bootstrapping a contextual LM with only a subset of the metadata during training retains 85% of the achievable gain. Training the model initially with proxy context retains 67% of the perplexity gain after adapting to real context. Furthermore, we can swap one type of pretrained sentence LM for another without retraining the context encoders, by only adapting the decoder model. Overall, we obtain a modular framework that allows incremental, scalable training of context-enhanced LMs.