Charles Lee

Soham Deshmukh, Charles Lee

Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are present. In such settings, conversation context can become a key disambiguating factor for detecting the user's request from the assistant. One prominent way of incorporating context is modeling past conversation history like task-oriented dialogue models. However, the nature of email conversations (long form) restricts direct usage of the latest advances in task-oriented dialogue models. So in this paper, we provide an effective transfer learning framework (EMToD) that allows the latest development in dialogue models to be adapted for long-form conversations. We show that the proposed EMToD framework improves intent detection performance over pre-trained language models by 45% and over pre-trained dialogue models by 30% for task-oriented email conversations. Additionally, the modular nature of the proposed framework allows plug-and-play for any future developments in both pre-trained language and task-oriented dialogue models.

Warren Johnson, Charles Lee

The economics of prompt compression depend not only on reducing input tokens but on how compression changes output length, which is typically priced several times higher. We evaluate this in a pre-registered six-arm randomized controlled trial of prompt compression on production multi-agent task-orchestration, analyzing 358 successful Claude Sonnet 4.5 runs (59-61 per arm) drawn from a randomized corpus of 1,199 real orchestration instructions. We compare an uncompressed control with three uniform retention rates (r=0.8, 0.5, 0.2) and two structure-aware strategies (entropy-adaptive and recency-weighted), measuring total inference cost (input+output) and embedding-based response similarity. Moderate compression (r=0.5) reduced mean total cost by 27.9%, while aggressive compression (r=0.2) increased mean cost by 1.8% despite substantial input reduction, consistent with small mean output expansion (1.03x vs. control) and heavy-tailed uncertainty. Recency-weighted compression achieved 23.5% savings and, together with moderate compression, occupied the empirical cost-similarity Pareto frontier, whereas aggressive compression was dominated on both cost and similarity. These results show that "compress more" is not a reliable production heuristic and that output tokens must be treated as a first-class outcome when designing compression policies.

Warren Johnson, Charles Lee

Selecting the appropriate model at inference time -- the routing problem -- requires jointly optimizing output quality, cost, latency, and governance constraints. Existing approaches delegate this decision to LLM-based classifiers or preference-trained routers that are themselves costly and high-latency, reducing a multi-objective optimization to single-dimensional quality prediction. We argue that small language models (SLMs, 1-4B parameters) have now achieved sufficient reasoning capability for sub-second, zero-marginal-cost, self-hosted task classification, potentially making the routing decision negligible in the inference budget. We test this thesis on a six-label taxonomy through two studies. Study 1 is a harmonized offline benchmark of Phi-3.5-mini, Qwen2.5-1.5B, and Qwen-2.5-3B on identical Azure T4 hardware, serving stack, quantization, and a fixed 60-case corpus. Qwen-2.5-3B achieves the best exact-match accuracy (0.783), the strongest latency-accuracy tradeoff, and the only nonzero accuracy on all six task families. Study 2 is a pre-registered four-arm randomized experiment under synthetic traffic with an effective sample size of 60 unique cases per arm, comparing Phi-4-mini, Qwen-2.5-3B, and DeepSeek-V3 against a no-routing control. DeepSeek-V3 attains the highest accuracy (0.830) but fails the pre-registered P95 latency gate (2,295 ms); Qwen-2.5-3B is Pareto-dominant among self-hosted models (0.793 accuracy, 988 ms median, $0 marginal cost). No model meets the standalone viability criterion (>=0.85 accuracy, <=2,000 ms P95). The cost and latency prerequisites for SLM-based routing are met; the accuracy gap of 6-8 percentage points and the untested question of whether correct classification translates to downstream output quality bound the remaining distance to production viability.

Joaquin Delgado Fernandez, Sergio Potenciano Menci, Charles Lee et al.

With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these forecasts as they provide detailed load data. However, using smart meter data for load forecasting is challenging due to data privacy requirements. This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation. For our analysis, we employ a large set of residential load data and simulate how different federated learning models and privacy preserving techniques affect performance and privacy. Our simulations reveal that combining federated learning and privacy preserving techniques can secure both high forecasting accuracy and near-complete privacy. Specifically, we find that such combinations enable a high level of information sharing while ensuring privacy of both the processed load data and forecasting models. Moreover, we identify and discuss challenges of applying federated learning, differential privacy and secure aggregation for residential short-term load forecasting.

Ruijie Zhou, Soham Deshmukh, Jeremiah Greer et al.

Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus on improving task-based conversational assistants online, primarily those working on document-type conversations (e.g., emails) whose contents may or may not be completely related to the assistant's task. We propose "NARLE" a deep reinforcement learning (RL) framework for improving the natural language understanding (NLU) component of dialogue systems online without the need to collect human labels for customer data. The proposed solution associates user emotion with the assistant's action and uses that to improve NLU models using policy gradients. For two intent classification problems, we empirically show that using reinforcement learning to fine tune the pre-trained supervised learning models improves performance up to 43%. Furthermore, we demonstrate the robustness of the method to partial and noisy implicit feedback.

Barun Patra, Chala Fufa, Pamela Bhattacharya et al.

State of the art research for date-time entity extraction from text is task agnostic. Consequently, while the methods proposed in literature perform well for generic date-time extraction from texts, they don't fare as well on task specific date-time entity extraction where only a subset of the date-time entities present in the text are pertinent to solving the task. Furthermore, some tasks require identifying negation constraints associated with the date-time entities to correctly reason over time. We showcase a novel model for extracting task-specific date-time entities along with their negation constraints. We show the efficacy of our method on the task of date-time understanding in the context of scheduling meetings for an email-based digital AI scheduling assistant. Our method achieves an absolute gain of 19\% f-score points compared to baseline methods in detecting the date-time entities relevant to scheduling meetings and a 4\% improvement over baseline methods for detecting negation constraints over date-time entities.

Vishwas Suryanarayanan, Barun Patra, Pamela Bhattacharya et al.

Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant. This makes it harder for the system to accurately detect intents, extract entities relevant to those intents and thereby perform the desired action. We present a neural model for scoping relevant information for the agent from a large query. We show that when used as a preprocessing step, the model improves performance of both intent detection and entity extraction tasks. We demonstrate the model's impact on Scheduler (Cortana is the persona of the agent, while Scheduler is the name of the service. We use them interchangeably in the context of this paper.) - a virtual conversational meeting scheduling assistant that interacts asynchronously with users through email. The model helps the entity extraction and intent detection tasks requisite by Scheduler achieve an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.