Traditional customer support systems, such as Interactive Voice Response (IVR), rely on rigid scripts and lack the flexibility required for handling complex, policy-driven tasks. While large language model (LLM) agents offer a promising alternative, evaluating their ability to act in accordance with business rules and real-world support workflows remains an open challenge. Existing benchmarks primarily focus on tool usage or task completion, overlooking an agent’s capacity to adhere to multi-step policies, navigate task dependencies, and remain robust to unpredictable user or environment behavior. In this work, we introduce JourneyBench, a benchmark designed to assess policy-aware agents in customer support. JourneyBench leverages graph representations to generate diverse, realistic support scenarios and proposes the User Journey Coverage Score, a novel metric to measure policy adherence. We evaluate multiple state-of-the-art LLMs using two agent designs: a Static-Prompt Agent (SPA) and a Dynamic-Prompt Agent (DPA) that explicitly models policy control. Across 703 conversations in three domains, we show that DPA significantly boosts policy adherence, even allowing smaller models like GPT-4o-mini to outperform more capable ones like GPT-4o. Our findings demonstrate the importance of structured orchestration and establish JourneyBench as a critical resource to advance AI-driven customer support beyond IVR-era limitations.

Much past work has focused on extracting information like events, entities, and relations from documents. Very little work has focused on analyzing these results for better model understanding. In this paper, we introduce a curation interface that takes an Information Extraction (IE) system’s output in a pre-defined format and generates a graphical representation of its elements. The interface supports editing while curating schemas for complex events like Improvised Explosive Device (IED) based scenarios. We identify various schemas that either have linear event chains or contain parallel events with complicated temporal ordering. We iteratively update an induced schema to uniquely identify events specific to it, add optional events around them, and prune unnecessary events. The resulting schemas are improved and enriched versions of the machine-induced versions.

We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video). The system advances state-of-the-art from two aspects: (1) extending from sentence-level event extraction to cross-document cross-lingual cross-media event extraction, coreference resolution and temporal event tracking; (2) using human curated event schema library to match and enhance the extraction output. We have made the dockerlized system publicly available for research purpose at GitHub, with a demo video.

Identifying a user’s location can be useful for recommendation systems, demographic analyses, and disaster outbreak monitoring. Although Twitter allows users to voluntarily reveal their location, such information isn’t universally available. Analyzing a tweet can provide a general estimation of a tweet location while giving insight into the dialect of the user and other linguistic markers. Such linguistic attributes can be used to provide a regional approximation of tweet origins. In this paper, we present a neural regression model that can identify the linguistic intricacies of a tweet to predict the location of the user. The final model identifies the dialect embedded in the tweet and predicts the location of the tweet.

Sequence-to-sequence models have proven to be highly successful in learning morphological inflection from examples as the series of SIGMORPHON/CoNLL shared tasks have shown. It is usually assumed, however, that a linguist working with inflectional examples could in principle develop a gold standard-level morphological analyzer and generator that would surpass a trained neural network model in accuracy of predictions, but that it may require significant amounts of human labor. In this paper, we discuss an experiment where a group of people with some linguistic training develop 25+ grammars as part of the shared task and weigh the cost/benefit ratio of developing grammars by hand. We also present tools that can help linguists triage difficult complex morphophonological phenomena within a language and hypothesize inflectional class membership. We conclude that a significant development effort by trained linguists to analyze and model morphophonological patterns are required in order to surpass the accuracy of neural models.