7 citations · 10 across the 8 of their papers we have counts for
8 papers
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces
Simon Yu, Derek Chong, Ananjan Nandi +4
As LLM agent systems take on more complex tasks, they increasingly rely on meta-agents: higher-order agents that create, operate on and manage other agents. Meta-agent operations s…
RL-Guided Data Selection for Language Model Finetuning
Animesh Jha, Harshit Gupta, Ananjan Nandi
Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict tr…
CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
Martijn Bartelds, Ananjan Nandi, Moussa Koulako Bala Doumbouya +3
Modern deep learning models often achieve high overall performance, but consistently fail on specific subgroups. Group distributionally robust optimization (group DRO) addresses th…
Sneaking Syntax into Transformer Language Models with Tree Regularization
Ananjan Nandi, Christopher D. Manning, Shikhar Murty
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 tr…
h4rm3l: A language for Composable Jailbreak Attack Synthesis
Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia +5
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…
Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles
Ryan Louie, Ananjan Nandi, William Fang +3
Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental h…
Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion
Ananjan Nandi, Navdeep Kaur, Parag Singla +1
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 inf…
DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion
Ananjan Nandi, Navdeep Kaur, Parag Singla +1
We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connect…