Papers by Kishaloy Halder

9 papers
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to gauge model’s uncertainty through self-consistency in responses to the target query are misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same query when answering a knowledge-preserving perturbation of the query.
Approach: They propose a method that uses multi-agent interaction to estimate black-box LLMs' uncertainty.
Outcome: The proposed method outperforms existing self-consistency based methods and improves hallucination detection.
Characterizing and Measuring Linguistic Dataset Drift (2023.acl-long)

Copied to clipboard

Challenge: Existing metrics for dataset drift have not considered specific dimensions of linguistic drift that affect model performance.
Approach: They propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift.
Outcome: The proposed metrics are more effective than previous metrics at predicting out-of-domain model accuracies compared to popular fine-tuned embedding distances .
Predicting Helpful Posts in Open-Ended Discussion Forums: A Neural Architecture (N19-1)

Copied to clipboard

Challenge: Unlike Community Question Answering, where questions are mostly factoid based, forum threads are often open-ended and contain repetitive or irrelevant posts.
Approach: They propose a recurrent neural network-based architecture to model the relevance of a post regarding the original post starting the thread and the novelty it brings to the discussion.
Outcome: The proposed model outperforms the state-of-the-art models for text classification on different types of online forum datasets.
A Weak Supervision Approach for Few-Shot Aspect Based Sentiment Analysis (2024.eacl-long)

Copied to clipboard

Challenge: Existing methods to improve few-shot performance in aspect-based sentiment analysis (ABSA) require complex interactions between the target and the polarity of the sentiment.
Approach: They propose a pipeline approach to construct a noisy ABSA dataset and adapt it to the ABSA tasks.
Outcome: The proposed model outperforms the state-of-the-art on the aspect extraction sentiment classification task and is capable of performing the harder aspect sentiment triplet extraction task.
Open Domain Question Answering with Conflicting Contexts (2025.findings-naacl)

Copied to clipboard

Challenge: Open domain question answering systems often rely on information retrieved from large collections of text to answer questions.
Approach: They evaluate and benchmark three powerful Large Language Models with a dataset . they find that 25% of unambiguous open domain questions can lead to conflicting contexts .
Outcome: The proposed model can't be used to answer questions with conflicting contexts . it can be fine tuned to provide richer information into the model's training .
MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrum (2026.findings-acl)

Copied to clipboard

Challenge: Existing training-time alignment methods require full retraining when a change is needed.
Approach: They propose an inference-time model-editing-based alignment method that learns encoded representations of preference dimensions and allows dynamic adjusting of the model behavior.
Outcome: The proposed method can be used to align large language models to human preferences . it reduces the cost of inference by half compared to the prompt engineering approach .
Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework (2020.coling-main)

Copied to clipboard

Challenge: 65% of job descriptions miss describing a significant number of relevant skills, a problem we address with a deep learning model based on a multi-label classification problem .
Approach: They propose a deep learning model to learn the set of enumerated job skills associated with a job description.
Outcome: The proposed model improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain.
Towards Long Context Hallucination Detection (2025.findings-naacl)

Copied to clipboard

Challenge: Large language models are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context.
Approach: They propose a dataset specifically designed for long-context hallucination detection.
Outcome: The proposed architecture outperforms existing models while providing faster inference.
Task-Aware Representation of Sentences for Generic Text Classification (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to text classification use a transformer architecture with a linear layer on top.
Approach: They propose a transformer-based approach that outputs a class distribution for a given prediction problem.
Outcome: The proposed model outperforms existing approaches on small training data and can learn to predict new classes even with no training examples.

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