Papers by Agam Shah
KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation (2026.acl-long)
Copied to clipboard
Nikita Tatarinov, Vidhyakshaya Kannan, Haricharana Srinivasa, Arnav Raj, Harpreet Singh Anand, Varun Singh, Aditya Luthra, Ravij Lade, Agam Shah, Sudheer Chava
| Challenge: | KG-MulQA extracts QA pairs at multiple complexity levels along three key dimensions: multi-hop retrieval, set operations, and answer plurality. |
| Approach: | They propose a framework that extracts QA pairs at multiple complexity levels along three key dimensions: multi-hop retrieval, set operations, and answer plurality. |
| Outcome: | The framework extracts QA pairs at multiple complexity levels along key dimensions . it enables fine-grained assessment of model performance across controlled difficulty levels. |
ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses (2025.emnlp-demos)
Copied to clipboard
Michael Galarnyk, Rutwik Routu, Vidhyakshaya Kannan, Kosha Bheda, Prasun Banerjee, Agam Shah, Sudheer Chava
| Challenge: | ARR Responsible NLP Research checklist is designed to encourage best practices for responsible research . previous research has shown that self-reported checklist responses don't always accurately represent papers . |
| Approach: | They propose a retrieval-augmented generation application that can be used to assist authors with conference checklists. |
| Outcome: | The proposed application can be used to help authors with conference checklists and review their work. |
Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks (2024.findings-emnlp)
Copied to clipboard
Yun-Shiuan Chuang, Krirk Nirunwiroj, Zach Studdiford, Agam Goyal, Vincent Frigo, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy Rogers
| Challenge: | Existing large language models can be prompted to role-play as individuals with particular demographic traits, but results are often human-like. |
| Approach: | They found that seeding LLM-based agents with a single belief improved alignment . they say that role-playing based on demographic information does not improve alignment a . |
| Outcome: | The proposed approach improves LLM alignment with human behavior . seeding agents with a single belief improves alignment for topics related to the belief network . |
CoCoHD: Congress Committee Hearing Dataset (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Congressional hearings are crucial tools for both political parties to advance their agendas. |
| Approach: | They propose a dataset covering congressional hearings from 1997 to 2024 across 86 committees, with 32,697 records. |
| Outcome: | The proposed dataset covers hearings from 1997 to 2024 across 86 committees, with 32,697 records. |
When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain (2022.emnlp-main)
Copied to clipboard
Raj Shah, Kunal Chawla, Dheeraj Eidnani, Agam Shah, Wendi Du, Sudheer Chava, Natraj Raman, Charese Smiley, Jiaao Chen, Diyi Yang
| Challenge: | Pre-trained language models have shown impressive performance on a variety of tasks and domains. |
| Approach: | They propose a domain specific financial LANGuage model which uses financial keywords and phrases for better masking. |
| Outcome: | The proposed model outperforms existing models on a variety of tasks and domains. |
How Inclusively do LMs Perceive Social and Moral Norms? (2025.findings-naacl)
Copied to clipboard
| Challenge: | Language models (LMs) are used in decision-making systems and as interactive assistants. |
| Approach: | They propose to prompt 11 LMs on rules-of-thumb and compare their outputs with 100 human annotators. |
| Outcome: | The proposed model is compared with 100 human annotators to find out if they are inclusive of diverse human values. |
Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis (2023.acl-long)
Copied to clipboard
| Challenge: | a study of FOMC pronouncements shows how important the FOMC communications are . hawkish-dovish classification is difficult because of the negative connotations of words . |
| Approach: | They propose to use a dataset to classify FOMC monetary policy stances . they construct a measure of monetary stance for the FOMC document release days . |
| Outcome: | The proposed model is based on a best-performing model and is available on Huggingface and GitHub under CC BY-NC 4.0 license. |
Simulating Opinion Dynamics with Networks of LLM-based Agents (2024.findings-naacl)
Copied to clipboard
Yun-Shiuan Chuang, Agam Goyal, Nikunj Harlalka, Siddharth Suresh, Robert Hawkins, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy Rogers
| Challenge: | Existing approaches to simulating opinion dynamics often over-simplify human behavior . authors propose refining LLMs with real-world discourse to better simulate evolution of beliefs . |
| Approach: | They propose to use large language models to simulate opinion dynamics in groups of simulated agents . they found that LLM agents produce more accurate information than ABMs . |
| Outcome: | The proposed model can be used to better simulate opinion dynamics in real-world discourses. |