Publications
Last Updated: September 2025.
An up to date list of all publications can be found on my Google Scholar profile.
2025

Dhananjay Ashok Ashutosh Chaubey, Hirona J. Arai, Jonathan May, Jesse Thomason
EMNLP 2025TLDR: While VLMs can recall factual associations when provided a textual reference to an entity, their ability to do so is halved when the reference is visual instead.
Selected Papers Grounding, Multimodality,
Dhananjay Ashok, Jonathan May
ACL 2025TLDR: Performance declines associated with replacing human generated data with synthetic data is most chronic only after crossing 90% replacement.
Selected Papers Grounding, Synthetic Data
Dhananjay Ashok, Jonathan May
NeurIPS 2025TLDR: Conformal probes trained on the hidden states of LMs can preemptively detect a variety of downstream behaviors, including susceptibility to jailbreaking, low confidence responses and alignment failures.
Selected Papers2024

Dhananjay Ashok, Barnabas Poczos
TLDR: We show that prior methods for controlling text generation of base Language Models perform worse than Instruction-Tuning. We also release ConGenBench, a testbed of more difficult controllable text generation problems.
Controllability2023

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos
EMNLP 2023TLDR: We combine synthetic data generation and score guided decoding to outperform GPT3 on Scientific Factual Error Correction.
Selected Papers Grounding, Synthetic Data
Matthew Barker, Emma Kallina, Dhananjay Ashok, Katherine Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen, Umang Bhatt
ACM EAAMO 2023TLDR: Introduces FeedbackLogs, an addenda to existing documentation of ML pipelines that tracks the input of multiple stakeholders.

Dhananjay Ashok, Zachary Chase Lipton
TLDR: We set the state-of-the-art in several FewShot and CrossDomain NER benchmarks with a Prompting approach.
Selected Papers Controllability, Domain Shift,2022

2021

Dhananjay Ashok, Joseph Scott, Sebastian J Wetzel, Maysum Panju, Vijay Ganesh
AAAI 2021TLDR: A data augmentation approach that uses prior knowledge to accelerate equation discovery.
Controllability, Grounding