Papers by Kishaloy Halder
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)
Copied to clipboard
Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth
| 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
Tyler Chang, Kishaloy Halder, Neha Anna John, Yogarshi Vyas, Yassine Benajiba, Miguel Ballesteros, Dan Roth
| 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
Robert Vacareanu, Siddharth Varia, Kishaloy Halder, Shuai Wang, Giovanni Paolini, Neha Anna John, Miguel Ballesteros, Smaranda Muresan
| 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
Siyi Liu, Qiang Ning, Kishaloy Halder, Zheng Qi, Wei Xiao, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth
| 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
Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss, Kishaloy Halder, Monica Sunkara, Manuel Mager, Yassine Benajiba
| 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
Siyi Liu, Kishaloy Halder, Zheng Qi, Wei Xiao, Nikolaos Pappas, Phu Mon Htut, Neha Anna John, Yassine Benajiba, Dan Roth
| 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. |