Papers by Disha Disha

6 papers
Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis (2026.eacl-long)

Copied to clipboard

Challenge: Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment.
Approach: They propose to examine LLMs’ internal representations rather than just their outputs to gain additional insights into potential membership inference signals.
Outcome: The proposed framework yields strong membership detection across several model families achieving average AUC scores of 0.85 on popular MIA benchmarks.
Don’t Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention (2024.emnlp-industry)

Copied to clipboard

Challenge: Large-scale language models (LLMs) are becoming increasingly popular in business scenarios, but maintaining topic continuity is a challenge.
Approach: They propose a topic continuity model that assesses whether a response aligns with the initial conversation topic using a Naive Bayes approach.
Outcome: The proposed model outperforms existing models in handling lengthy and complex conversations.
BIG-Bench Extra Hard (2025.acl-long)

Copied to clipboard

Challenge: Current benchmarks for large language model reasoning focus on math and coding abilities, leaving a gap in evaluating broader reasoning proficiencies.
Approach: They propose a benchmark to evaluate general reasoning in large language models . they use BIG-Bench and its harder version BIG-Benefit Hard to assess general reasoning .
Outcome: The new benchmark pushes the boundaries of LLM reasoning evaluation.
Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection (2020.coling-main)

Copied to clipboard

Challenge: Existing work on identifying the salient information in a text has used a limited representation of events that omits essential information.
Approach: They propose a highly contextual model of event salience that uses a rich representation of events and integrates document-level information.
Outcome: The proposed model improves on an event salience dataset by 2-4% on standard metrics and addresses flaws in existing evaluation methodologies.
Annotation of a Large Clinical Entity Corpus (D18-1)

Copied to clipboard

Challenge: Past researches have shown the superiority of statistical/ML approaches over the rule based approaches.
Approach: They propose to annotate a clinical domain annotated corpus using a small data set or a narrower domain to take full advantage of machine learning.
Outcome: The proposed corpus contains 5,160 clinical documents from forty different clinical specialties.
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages (2021.findings-acl)

Copied to clipboard

Challenge: Model-agnostic meta-learning (MAML) is a strategy to learn resource-poor languages in a sample-efficient fashion.
Approach: They propose a model-agnostic meta-learning strategy that minimizes the expected risk across languages with a uniform prior . they propose 'minimax' and 'neyman-pearson' models that constrain the risk in each language to a maximum threshold.
Outcome: The proposed model reduces the maximum risk across languages while constraining the risk in each language to a maximum threshold.

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