Papers by Hemank Lamba

6 papers
Uchaguzi-2022: A Dataset of Citizen Reports on the 2022 Kenyan Election (2025.coling-main)

Copied to clipboard

Challenge: Systematically organizing and geotagging large amounts of crowdsourced information requires substantial manual effort, often led by volunteers.
Approach: They present a dataset of 14k citizen reports related to the 2022 Kenyan General Election . they investigate whether language models can assist in scalably categorizing and geotagging reports .
Outcome: The proposed dataset aims to show whether language models can assist in categorizing and geotagging reports, thus highlighting its potential application in the AI for Social Good space.
Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Neural ranking models produce the final document scores, but they are often treated as transient information and only the relative orderings are preserved to produce a ranking.
Approach: They propose to exploit large language models (LLMs) to provide relevance and uncertainty signals for these neural text rankers to produce scale-calibrated scores through Monte Carlo sampling of natural language explanations (NLEs).
Outcome: The proposed approach outperforms previous calibration methods and LLM-based methods for ranking, calibration, and query performance prediction tasks.
Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions (2025.emnlp-main)

Copied to clipboard

Challenge: Exact label definitions are considered as clues to disambiguate unclear labels, helping models perform their tasks more effectively.
Approach: They conducted controlled experiments on multiple explanation benchmark datasets and label definition conditions using expert-curated, LLM-generated, perturbed, and swapped definitions.
Outcome: The results suggest that models often default to internal representations, particularly in general tasks, while domain-specific tasks benefit more from explicit definitions.
HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid (2024.findings-emnlp)

Copied to clipboard

Challenge: Humanitarian organizations can analyze data to discover trends, gather aggregated insights, manage security risks, and inform advocacy and funding proposals.
Approach: They present a dataset comprising news articles in three languages containing instances of different types of violent incidents categorized by the humanitarian sector they impact.
Outcome: The proposed framework can be used to identify violent incidents and identify their impact on humanitarian operations.
CEHA: A Dataset of Conflict Events in the Horn of Africa (2025.coling-main)

Copied to clipboard

Challenge: Existing datasets categorizing conflict events do not cover all of the fine-grained types of conflict relevant to areas like the Horn of Africa.
Approach: They propose to use online news articles to categorize violent conflict events . they propose to extract event-relevance and event-types from 500 English event descriptions .
Outcome: The proposed dataset categorizes conflict risk according to specific areas required by stakeholders in the Humanitarian-Peace-Development Nexus.

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