Dhaval Patel

Yifan Zhang, Giridhar Ganapavarapu, Srideepika Jayaraman et al.

Large Language Models (LLMs) often falter at complex planning tasks that require exploration and self-correction, as their linear reasoning process struggles to recover from early mistakes. While search algorithms like Monte Carlo Tree Search (MCTS) can explore alternatives, they are often ineffective when guided by sparse rewards and fail to leverage the rich semantic capabilities of LLMs. We introduce SPIRAL (Symbolic LLM Planning via Grounded and Reflective Search), a novel framework that embeds a cognitive architecture of three specialized LLM agents into an MCTS loop. SPIRAL's key contribution is its integrated planning pipeline where a Planner proposes creative next steps, a Simulator grounds the search by predicting realistic outcomes, and a Critic provides dense reward signals through reflection. This synergy transforms MCTS from a brute-force search into a guided, self-correcting reasoning process. On the DailyLifeAPIs and HuggingFace datasets, SPIRAL consistently outperforms the default Chain-of-Thought planning method and other state-of-the-art agents. More importantly, it substantially surpasses other state-of-the-art agents; for example, SPIRAL achieves 83.6% overall accuracy on DailyLifeAPIs, an improvement of over 16 percentage points against the next-best search framework, while also demonstrating superior token efficiency. Our work demonstrates that structuring LLM reasoning as a guided, reflective, and grounded search process yields more robust and efficient autonomous planners. The source code, full appendices, and all experimental data are available for reproducibility at the official project repository.

Christodoulos Constantinides, Dhaval Patel, Shuxin Lin et al.

We introduce FailureSensorIQ, a novel Multi-Choice Question-Answering (MCQA) benchmarking system designed to assess the ability of Large Language Models (LLMs) to reason and understand complex, domain-specific scenarios in Industry 4.0. Unlike traditional QA benchmarks, our system focuses on multiple aspects of reasoning through failure modes, sensor data, and the relationships between them across various industrial assets. Through this work, we envision a paradigm shift where modeling decisions are not only data-driven using statistical tools like correlation analysis and significance tests, but also domain-driven by specialized LLMs which can reason about the key contributors and useful patterns that can be captured with feature engineering. We evaluate the Industrial knowledge of over a dozen LLMs-including GPT-4, Llama, and Mistral-on FailureSensorIQ from different lens using Perturbation-Uncertainty-Complexity analysis, Expert Evaluation study, Asset-Specific Knowledge Gap analysis, ReAct agent using external knowledge-bases. Even though closed-source models with strong reasoning capabilities approach expert-level performance, the comprehensive benchmark reveals a significant drop in performance that is fragile to perturbations, distractions, and inherent knowledge gaps in the models. We also provide a real-world case study of how LLMs can drive the modeling decisions on 3 different failure prediction datasets related to various assets. We release: (a) expert-curated MCQA for various industrial assets, (b) FailureSensorIQ benchmark and Hugging Face leaderboard based on MCQA built from non-textual data found in ISO documents, and (c) LLMFeatureSelector, an LLM-based feature selection scikit-learn pipeline. The software is available at https://github.com/IBM/FailureSensorIQ.

Shuxin Lin, Dhaval Patel, Christodoulos Constantinides

Small Language Models (SLMs) are becoming increasingly popular in specialized fields, such as industrial applications, due to their efficiency, lower computational requirements, and ability to be fine-tuned for domain-specific tasks, enabling accurate and cost-effective solutions. However, performing complex reasoning using SLMs in specialized fields such as Industry 4.0 remains challenging. In this paper, we propose a knowledge distillation framework for industrial asset health, which transfers reasoning capabilities via Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) to smaller, more efficient models (SLMs). We discuss the advantages and the process of distilling LLMs using multi-choice question answering (MCQA) prompts to enhance reasoning and refine decision-making. We also perform in-context learning to verify the quality of the generated knowledge and benchmark the performance of fine-tuned SLMs with generated knowledge against widely used LLMs. The results show that the fine-tuned SLMs with CoT reasoning outperform the base models by a significant margin, narrowing the gap to their LLM counterparts. Our code is open-sourced at: https://github.com/IBM/FailureSensorIQ.

Nimesh Jha, Shuxin Lin, Srideepika Jayaraman et al. · ibm-research

This paper introduces a scalable Anomaly Detection Service with a generalizable API tailored for industrial time-series data, designed to assist Site Reliability Engineers (SREs) in managing cloud infrastructure. The service enables efficient anomaly detection in complex data streams, supporting proactive identification and resolution of issues. Furthermore, it presents an innovative approach to anomaly modeling in cloud infrastructure by utilizing Large Language Models (LLMs) to understand key components, their failure modes, and behaviors. A suite of algorithms for detecting anomalies is offered in univariate and multivariate time series data, including regression-based, mixture-model-based, and semi-supervised approaches. We provide insights into the usage patterns of the service, with over 500 users and 200,000 API calls in a year. The service has been successfully applied in various industrial settings, including IoT-based AI applications. We have also evaluated our system on public anomaly benchmarks to show its effectiveness. By leveraging it, SREs can proactively identify potential issues before they escalate, reducing downtime and improving response times to incidents, ultimately enhancing the overall customer experience. We plan to extend the system to include time series foundation models, enabling zero-shot anomaly detection capabilities.

Christodoulos Constantinides, Shuxin Lin, Dhaval Patel

In this work we focus on improving language models' understanding for asset maintenance to guide the engineer's decisions and minimize asset downtime. Given a set of tasks expressed in natural language for Industry 4.0 domain, each associated with queries related to a specific asset, we want to recommend relevant items and generalize to queries of similar assets. A task may involve identifying relevant sensors given a query about an asset's failure mode. Our approach begins with gathering a qualitative, expert-vetted knowledge base to construct nine asset-specific task datasets. To create more contextually informed embeddings, we augment the input tasks using Large Language Models (LLMs), providing concise descriptions of the entities involved in the queries. This embedding model is then integrated with a Reasoning and Acting agent (ReAct), which serves as a powerful tool for answering complex user queries that require multi-step reasoning, planning, and knowledge inference. Through ablation studies, we demonstrate that: (a) LLM query augmentation improves the quality of embeddings, (b) Contrastive loss and other methods that avoid in-batch negatives are superior for datasets with queries related to many items, and (c) It is crucial to balance positive and negative in-batch samples. After training and testing on our dataset, we observe a substantial improvement: HIT@1 increases by +54.2%, MAP@100 by +50.1%, and NDCG@10 by +54.7%, averaged across all tasks and models. Additionally, we empirically demonstrate the model's planning and tool invocation capabilities when answering complex questions related to industrial asset maintenance, showcasing its effectiveness in supporting Subject Matter Experts (SMEs) in their day-to-day operations.

Christodoulos Constantinides, Shuxin Lin, Nianjun Zhou et al.

This paper presents a novel multi-agent system called Chat-of-Thought, designed to facilitate the generation of Failure Modes and Effects Analysis (FMEA) documents for industrial assets. Chat-of-Thought employs multiple collaborative Large Language Model (LLM)-based agents with specific roles, leveraging advanced AI techniques and dynamic task routing to optimize the generation and validation of FMEA tables. A key innovation in this system is the introduction of a Chat of Thought, where dynamic, multi-persona-driven discussions enable iterative refinement of content. This research explores the application domain of industrial equipment monitoring, highlights key challenges, and demonstrates the potential of Chat-of-Thought in addressing these challenges through interactive, template-driven workflows and context-aware agent collaboration.

Sachin, Dhaval Patel

Query suggestion refers to the task of suggesting relevant and related queries to a search engine user to help in query formulation process and to expedite information retrieval with minimum amount of effort. It is highly useful in situations where the search requirements are not well understood and hence it has been widely adopted by search engines to guide users' search activity. For news websites, user queries have a time sensitive nature inherent in them. When some new event happens, there is a sudden burst in queries related to that event and such queries are sustained over a period of time before fading away with that event. In addition to this temporal aspect of search queries fired at news websites, they have an addition distinct quality, i.e., they are intended to get event related information majority of the times. Existing work on generating query suggestions involves analyzing query logs to suggest queries which are relevant and related to the search intent of the user. But in case of news websites, when there is a sudden burst in information related to a particular event, there are not enough search queries fired by other users which leads to lack of click data, and hence giving query suggestions related to some old event or even some irrelevant suggestions altogether. Another problem with query logs in the context of online news is that, they mostly contain queries related to popular events and hence fail to capture less popular events or events which got overshadowed by some other more sensational event. We propose a novel approach to generate event-centric query suggestions using metadata of news articles published by news media. We compared our proposed framework with existing state of the art query suggestion mechanisms provided by Google News, Bing News, Google Search and Bing Search on various parameters.

Rohan Kabra, Divya Saxena, Dhaval Patel et al.

Human behavior modeling deals with learning and understanding behavior patterns inherent in humans' daily routines. Existing pattern mining techniques either assume human dynamics is strictly periodic, or require the number of modes as input, or do not consider uncertainty in the sensor data. To handle these issues, in this paper, we propose a novel clustering approach for modeling human behavior (named, MTpattern) from time-series data. For mining frequent human behavior patterns effectively, we utilize a three-stage pipeline: (1) represent time series data into a sequence of regularly sampled equal-sized unit time intervals for better analysis, (2) a new distance measure scheme is proposed to cluster similar sequences which can handle temporal variation and uncertainty in the data, and (3) exploit an exemplar-based clustering mechanism and fine-tune its parameters to output minimum number of clusters with given permissible distance constraints and without knowing the number of modes present in the data. Then, the average of all sequences in a cluster is considered as a human behavior pattern. Empirical studies on two real-world datasets and a simulated dataset demonstrate the effectiveness of MTpattern with respect to internal and external measures of clustering.

Syed Yousaf Shah, Dhaval Patel, Long Vu et al.

A large number of time series forecasting models including traditional statistical models, machine learning models and more recently deep learning have been proposed in the literature. However, choosing the right model along with good parameter values that performs well on a given data is still challenging. Automatically providing a good set of models to users for a given dataset saves both time and effort from using trial-and-error approaches with a wide variety of available models along with parameter optimization. We present AutoAI for Time Series Forecasting (AutoAI-TS) that provides users with a zero configuration (zero-conf ) system to efficiently train, optimize and choose best forecasting model among various classes of models for the given dataset. With its flexible zero-conf design, AutoAI-TS automatically performs all the data preparation, model creation, parameter optimization, training and model selection for users and provides a trained model that is ready to use. For given data, AutoAI-TS utilizes a wide variety of models including classical statistical models, Machine Learning (ML) models, statistical-ML hybrid models and deep learning models along with various transformations to create forecasting pipelines. It then evaluates and ranks pipelines using the proposed T-Daub mechanism to choose the best pipeline. The paper describe in detail all the technical aspects of AutoAI-TS along with extensive benchmarking on a variety of real world data sets for various use-cases. Benchmark results show that AutoAI-TS, with no manual configuration from the user, automatically trains and selects pipelines that on average outperform existing state-of-the-art time series forecasting toolkits.

George Zerveas, Srideepika Jayaraman, Dhaval Patel et al.

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and classification, forecasting and missing value imputation. By evaluating our models on several benchmark datasets for multivariate time series regression and classification, we show that not only does our modeling approach represent the most successful method employing unsupervised learning of multivariate time series presented to date, but also that it exceeds the current state-of-the-art performance of supervised methods; it does so even when the number of training samples is very limited, while offering computational efficiency. Finally, we demonstrate that unsupervised pre-training of our transformer models offers a substantial performance benefit over fully supervised learning, even without leveraging additional unlabeled data, i.e., by reusing the same data samples through the unsupervised objective.

Nikita Jain, Swati Gupta, Dhaval Patel

This paper presents a novel system E3 for extracting keyphrases from news content for the purpose of offering the news audience a broad overview of news events, with especially high content volume. Given an input query, E3 extracts keyphrases and enrich them by tagging, ranking and finding role for frequently associated keyphrases. Also, E3 finds the novelty and activeness of keyphrases using news publication date, to identify the most interesting and informative keyphrases.

Abhay Prakash, Dhaval Patel

Query Understanding concerns about inferring the precise intent of search by the user with his formulated query, which is challenging because the queries are often very short and ambiguous. The report discusses the various kind of queries that can be put to a Search Engine and illustrates the Role of Query Understanding for return of relevant results. With different advances in techniques for deep understanding of queries as well as documents, the Search Technology has witnessed three major era. A lot of interesting real world examples have been used to illustrate the role of Query Understanding in each of them. The Query Understanding Module is responsible to correct the mistakes done by user in the query, to guide him in formulation of query with precise intent, and to precisely infer the intent of the user query. The report describes the complete architecture to handle aforementioned three tasks, and then discusses basic as well as recent advanced techniques for each of the component, through appropriate papers from reputed conferences and journals.