Publications by Tags

, , ,

Selected Papers

A Little Human Data Goes a Long Way

Dhananjay Ashok, Jonathan May


TLDR: Performance declines associated with replacing human generated data with synthetic data is most chronic only after crossing 90% replacement.

,

SciFix: Outperforming GPT3 on Scientific Factual Error Correction

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos

EMNLP 2023

TLDR: We combine synthetic data generation and score guided decoding to outperform GPT3 on Scientific Factual Error Correction.

,

PromptNER: Prompting For FewShot Named Entity Recognition

Dhananjay Ashok, Zachary Chase Lipton


TLDR: We set the state-of-the-art in several FewShot and CrossDomain NER benchmarks with a Prompting approach.

, ,

Controllability

Controllable Text Generation in the Instruction Tuning Era

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.



PromptNER: Prompting For FewShot Named Entity Recognition

Dhananjay Ashok, Zachary Chase Lipton


TLDR: We set the state-of-the-art in several FewShot and CrossDomain NER benchmarks with a Prompting approach.

, ,

Logic guided genetic algorithms

Dhananjay Ashok, Joseph Scott, Sebastian J Wetzel, Maysum Panju, Vijay Ganesh

AAAI 2021

TLDR: A data augmentation approach that uses prior knowledge to accelerate equation discovery.

,

Domain Shift

PromptNER: Prompting For FewShot Named Entity Recognition

Dhananjay Ashok, Zachary Chase Lipton


TLDR: We set the state-of-the-art in several FewShot and CrossDomain NER benchmarks with a Prompting approach.

, ,

Grounding

A Little Human Data Goes a Long Way

Dhananjay Ashok, Jonathan May


TLDR: Performance declines associated with replacing human generated data with synthetic data is most chronic only after crossing 90% replacement.

,

SciFix: Outperforming GPT3 on Scientific Factual Error Correction

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos

EMNLP 2023

TLDR: We combine synthetic data generation and score guided decoding to outperform GPT3 on Scientific Factual Error Correction.

,

Logic guided genetic algorithms

Dhananjay Ashok, Joseph Scott, Sebastian J Wetzel, Maysum Panju, Vijay Ganesh

AAAI 2021

TLDR: A data augmentation approach that uses prior knowledge to accelerate equation discovery.

,

Synthetic Data

A Little Human Data Goes a Long Way

Dhananjay Ashok, Jonathan May


TLDR: Performance declines associated with replacing human generated data with synthetic data is most chronic only after crossing 90% replacement.

,

SciFix: Outperforming GPT3 on Scientific Factual Error Correction

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos

EMNLP 2023

TLDR: We combine synthetic data generation and score guided decoding to outperform GPT3 on Scientific Factual Error Correction.

,