Papers by Aman Chadha

23 papers
FACTIFY3M: A benchmark for multimodal fact verification with explainability through 5W Question-Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Disinformation can cause disruption in the share market, panic and anxiety in society, and even death during crises.
Approach: a new dataset is being developed to help combat disinformation . the dataset is a multimodal fake news dataset with 5W question-answering .
Outcome: FACTIFY 3M is the largest dataset and benchmark for multimodal fact verification.
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings (2025.coling-main)

Copied to clipboard

Challenge: Existing work in this field has looked most commonly into gender bias, racial bias, and religious bias.
Approach: They propose an algorithm that uses a neural network to perform ‘soft debiasing’ and build on the seminal work of (CITATION) and (CitATION).
Outcome: The proposed algorithm outperforms current methods on gender, race, and religion metrics on a wide range of metrics.
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting (2025.coling-main)

Copied to clipboard

Challenge: Proportional analogies are used to assess linguistic and cognitive abilities.
Approach: They propose a dataset for proportional analogy completion and evaluate its performance in large-scale learning environments.
Outcome: The proposed model achieves 55% accuracy in knowledge-enhanced prompts.
ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs (2024.findings-emnlp)

Copied to clipboard

Challenge: Despite the fact that many fact-checking tools lack granularity and explainability, they lack the ability to be useful in various contexts.
Approach: They propose a text validation framework that provides granular explanations for each claim and localizes the specific problematic content to reduce cognitive load.
Outcome: The proposed framework provides granular explanations for each claim prediction and localizes and educates users on the specific content.
YinYang-Align: A new Benchmark for Competing Objectives and Introducing Multi-Objective Preference based Text-to-Image Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Recent controversies highlight the need for robust alignment mechanisms in text-to-image systems.
Approach: They propose a framework to evaluate T2I systems across six contradictory alignment objectives . objectives highlight key trade-offs such as artistic freedom and cultural sensitivity .
Outcome: The proposed framework achieves superior alignment across all objectives.
Counter Turing Test (CT2): AI-Generated Text Detection is Not as Easy as You May Think - Introducing AI Detectability Index (ADI) (2023.emnlp-main)

Copied to clipboard

Challenge: a number of issues have arisen regarding the risk and consequences of AI-generated text detection.
Approach: They propose a counter-turing test to evaluate the robustness of existing AGTD methods . they propose ADI, a quantifiable spectrum to assess detectability of LLMs .
Outcome: The proposed method evaluates the robustness of existing AGTD methods . it shows that larger LLMs tend to have lower ADI, indicating they are less detectable .
On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models (2024.findings-eacl)

Copied to clipboard

Challenge: Analogies facilitate the transfer of meaning and knowledge from one domain to another.
Approach: They propose to use large language models to encode syntactic and semantic structures of sentences to identify sentence analogies.
Outcome: The LLMs which capture syntactic structures better, also have higher abilities in identifying sentence analogies.
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Direct Preference Optimization (DPO) is a cornerstone for preference alignment but is constrained by fixed divergence measures and limited feature transformations.
Approach: They propose a new enhancement of Direct Preference Optimization that integrates kernel methods to overcome these challenges.
Outcome: The proposed model improves divergence measures and features by using kernels . the proposed model achieves state-of-the-art generalization in factuality, safety, reasoning, and instruction following .
Tutorial Proposal: Hallucination in Large Language Models (2024.lrec-tutorials)

Copied to clipboard

Challenge: Grasping the intricacies of hallucination in LLMs can be daunting, especially for those new to the field.
Approach: This tutorial aims to bridge the gap between the field and the field of hallucination . it will explore the key aspects of hallucinonation, including benchmarking, detection, and mitigation techniques .
Outcome: This tutorial will explore the key aspects of hallucination in LLMs . it will also explore the specific constraints and shortcomings of current approaches .
Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations (2025.emnlp-main)

Copied to clipboard

Challenge: a new metric measures the quality of large language models (LLMs) that detects hidden misalignments and jailbreak risks.
Approach: They propose a decoding-invariant metric that measures latent safety failures . they propose 'Alignment Quality Index' to measure latent activations in latent space .
Outcome: The proposed metric detects latent safety failures overlooked by behavioral benchmarks and jailbreaks.
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have demonstrated strong potential for understanding user intent . paper describes system architecture, agent roles, retrieval and scoring methods, knowledge graph schema, and evaluation interfaces .
Approach: They propose a multi-agent research discovery and analysis system that integrates multiple agents to reduce the effort required to find, assess, organize, and understand academic literature.
Outcome: The proposed system reduces the effort required to find, assess, organize, and understand academic literature.
The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models have generated widespread acclaim, but hallucination has also emerged as a by-product.
Approach: They propose a fine-grained discourse on profiling hallucination based on its degree, orientation, and category . they categorize hallucines into six types: acronym ambiguity, generated golem, virtual voice, geographic erratum, time wrap .
Outcome: The proposed method categorizes hallucination into six types based on their degree, orientation, and category .
DM-Codec: Distilling Multimodal Representations for Speech Tokenization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing speech tokenization models lack contextual representations for speech synthesis . absence of contextual representation results in elevated WER and WIL scores .
Approach: They propose a language model-guided distillation method that incorporates contextual information into a comprehensive speech tokenizer.
Outcome: The proposed method outperforms state-of-the-art tokenization models in reducing WER and WIL scores.
Enhancing Adverse Drug Event Detection with Multimodal Dataset: Corpus Creation and Model Development (2024.findings-acl)

Copied to clipboard

Challenge: ADEs are a serious public health concern and cost healthcare systems billions of dollars . despite advancements in healthcare, ADE detection remains a significant challenge .
Approach: They propose a multimodal adverse drug event detection dataset that merges ADE-related textual information with visual aids to enhance patient safety.
Outcome: The proposed dataset integrates ADE-related textual information with visual aids to improve patient safety and healthcare accessibility.
MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention (2024.acl-long)

Copied to clipboard

Challenge: Existing studies on content moderation of toxic memes focus on text-based content . current research neglects the widespread influence of multimodal content like memes .
Approach: They propose a framework leveraging Large Language Models and Visual Language Model (VLMs) for meme intervention.
Outcome: The proposed framework enables users to generate relevant and effective responses to toxic memes.
Can Large Language Models Infer Causal Relationships from Real-World Text? (2026.acl-long)

Copied to clipboard

Challenge: Existing work evaluating large language models relies on synthetic or simplified texts with explicit causal relationships.
Approach: They develop a benchmark to evaluate LLMs' ability to infer causal relationships from texts . they use a dataset of texts with different levels of explicitness and complexity .
Outcome: The proposed benchmark is the first-ever real-world dataset for this task.
Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering (2024.eacl-srw)

Copied to clipboard

Challenge: Existing domain adaptation methods do not account for unseen natural distribution shifts.
Approach: They perform experiments on 4 different datasets under varying amounts of distribution shift . they analyze how "in-the-wild" generation can help achieve domain generalization .
Outcome: The proposed approach augments reading comprehension datasets with generated data to improve robustness towards natural distribution shifts.
SEPSIS: I Can Catch Your Lies – A New Paradigm for Deception Detection (2025.acl-srw)

Copied to clipboard

Challenge: a new framework categorizes deception into three forms: lies of omission, lies of commission, and lies of influence . a novel framework for deception detection leveraging NLP techniques is proposed .
Approach: They propose a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence.
Outcome: The proposed framework achieves an impressive F1 score of 0.87 across all layers . it can be used to investigate lies of omission, lies of commission and lies of influence .
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models enable them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
Approach: They propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a model that incorporates both generic and specific personas.
Outcome: The proposed model systematically measures persona biases in harmful expression and harmful agreement.
FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Contemporary fact-checking systems focus on estimating truthfulness using numerical scores which are not human-interpretable.
Approach: They propose a 5W framework for question-answer-based fact explainability that can assist human fact-checkers in asking relevant questions . they propose masked language model which generates QA pairs for claims and a baseline QA system that automatically locates those answers from evidence documents.
Outcome: The proposed framework can assist human fact-checkers in asking relevant questions related to a fact, which can then be validated separately to reach a final verdict.
Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges (2024.acl-srw)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive zero-shot performance on a wide range of NLP tasks.
Approach: They propose to use large language models to augment extractive reading comprehension datasets by fine-tuning their annotations and comparing their performance to human annotators.
Outcome: The proposed model can be used to augment extractive reading comprehension datasets.
ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Modern large language models are evaluated on extrinsic measures based on benchmarks such as GLUE and SuperGLUE.
Approach: They propose a benchmark to intrinsically evaluate large language models across a taxonomy of analogies of long text with six levels of complexity.
Outcome: The proposed benchmark evaluates LLMs across a taxonomy of analogies of long text with six levels of complexity.
A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models (2024.findings-emnlp)

Copied to clipboard

Challenge: a growing need to understand and alleviate FMs' propensity to produce hallucinated outputs, especially in high-stakes applications.
Approach: They propose a framework for detecting and mitigating hallucination in FMs . they synthesize recent advancements in detection and mitigation techniques .
Outcome: The proposed framework provides valuable insights for researchers, developers, and practitioners.

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