Papers by Vatche Isahagian
FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows (2025.emnlp-industry)
Copied to clipboard
Evelyn Duesterwald, Siyu Huo, Vatche Isahagian, K. R. Jayaram, Ritesh Kumar, Vinod Muthusamy, Punleuk Oum, Debashish Saha, Gegi Thomas, Praveen Venkateswaran
| Challenge: | Large Language Models (LLMs) can be used to convert natural language (NL) instructions into structured business process automation (BPA) process artifacts. |
| Approach: | They propose to use large language models to convert natural language (NL) instructions into structured business process automation (BPA) process artifacts. |
| Outcome: | The proposed model can be used to translate NL into Python and convert it into widely adopted business process definition languages. |
OptiSeq: Ordering Examples On-The-Fly for In-Context Learning (2025.findings-emnlp)
Copied to clipboard
Rahul Atul Bhope, Praveen Venkateswaran, K. R. Jayaram, Vatche Isahagian, Vinod Muthusamy, Nalini Venkatasubramanian
| Challenge: | In-context-learning (ICL) is fragile and requires a lot of examples to perform. |
| Approach: | They propose a purely inference-time, dataset-free optimization method that efficiently determines the best example order. |
| Outcome: | The proposed method improves in-context-learning accuracy by 5.5 - 10.5 percentage points across multiple tasks. |
Towards large language model-based personal agents in the enterprise: Current trends and open problems (2023.findings-emnlp)
Copied to clipboard
Vinod Muthusamy, Yara Rizk, Kiran Kate, Praveen Venkateswaran, Vatche Isahagian, Ashu Gulati, Parijat Dube
| Challenge: | Existing large language models (LLMs) are brittle to input changes and can produce inconsistent results for the same inputs. |
| Approach: | They propose to use large language models to reason about complex goals and orchestrate a set of pluggable tools or APIs to accomplish a goal. |
| Outcome: | The proposed use cases have many open problems in an exciting area of NLP research, such as trust and explainability, consistency and reproducibility, and the need for new metrics and benchmarks. |
TaskDiff: A Similarity Metric for Task-Oriented Conversations (2023.emnlp-main)
Copied to clipboard
| Challenge: | Popularity of chatGPT and Llama 2 has led to a race to build custom task-oriented conversational assistants in enterprise domains like finance and retail. |
| Approach: | They propose a conversational similarity metric that uses different dialogue components to compute similarity. |
| Outcome: | Experiments on a benchmark dataset show that the proposed metric outperforms existing approaches and is more robust than previous approaches. |
DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to task-oriented conversation system DST use hand-crafted templates and additional slot information to fine-tune and prompt large pre-trained language models and elicit slot values from the dialogue context. |
| Approach: | They propose a generalizable in-context tuning approach that retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. |
| Outcome: | Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings using a much smaller model. |