AIConfPaper
← Search

Ananjan Nandi

6 accepted papers

2026

CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition

Martijn Bartelds, Ananjan Nandi, Moussa Koulako Bala Doumbouya, Dan Jurafsky, Tatsunori Hashimoto, Karen Livescu
ICLR 2026poster

Modern deep learning models often achieve high overall performance, but consistently fail on specific subgroups. Group distributionally robust optimization (group DRO) addresses this problem by minimizing the worst-group loss, but it fails when group losses misrepresent performance differences betwe…

Cited by 0Source ↗code ↗Scholar ↗
2025

Sneaking Syntax into Transformer Language Models with Tree Regularization

Ananjan Nandi, Christopher D Manning, Shikhar Murty
NAACL 2025long

While compositional accounts of human language understanding are based on a hierarchical tree-like process, neural models like transformers lack a direct inductive bias for such tree structures. Introducing syntactic inductive biases could unlock more robust and data-efficient learning in transforme…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

h4rm3l: A Language for Composable Jailbreak Attack Synthesis

Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi +2
ICLR 2025poster

Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the ineffectiveness of their safety filters, which can be bypassed by prompt transformations called jailbreak attacks. Curre…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam .
ACL 2024short

We consider two popular approaches to KnowledgeGraph Completion (KGC): textual modelsthat rely on textual entity descriptions, andstructure-based models that exploit the connectivitystructure of the Knowledge Graph(KG). Preliminary experiments show that theseapproaches have complementary strengths:s…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles

Ryan Louie, Ananjan Nandi, William Fang, Cheng Chang, Emma Brunskill, Diyi Yang
EMNLP 2024main

Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in the domain of mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vit…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2023

Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam
ACL 2023short

High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural models for generating rule sets, however, preliminary experiments show that the…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗