Papers by Agam Shah

8 papers
KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation (2026.acl-long)

Copied to clipboard

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations