AIConfPaper
← Search

Soundararajan Srinivasan

4 accepted papers

2025

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

Emmanuel Aboah Boateng, Cassiano O Becker, Nabiha Asghar, Kabir Walia, Ashwin Srinivasan, Ehi Nosakhare +2
NAACL 2025industry

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts need to be updated to re-optimize the task performance. We…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

On Surgical Fine-tuning for Language Encoders

Abhilasha Lodha, Gayatri Vyankatesh Belapurkar, Saloni Chalkapurkar, Yuanming Tao, Reshmi Ghosh, Samyadeep Basu +2
EMNLP 2023short findings

Fine-tuning all the layers of a pre-trained neural language encoder (either using all the parameters or using parameter-efficient methods) is often the de-facto way of adapting it to a new task. We show evidence that for different downstream language tasks, fine-tuning only a subset of layers is suf…

Cited by 0Source ↗code ↗Scholar ↗
2022

On Optimizing Interventions in Shared Autonomy

Weihao Tan, David Koleczek, Siddhant Pradhan, Nicholas Perello, Vivek Chettiar, Vishal Rohra +4
AAAI 2022technical

Shared autonomy refers to approaches for enabling an autonomous agent to collaborate with a human with the aim of improving human performance. However, besides improving performance, it may often also be beneficial that the agent concurrently accounts for preserving the user’s experience or satisfac…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2022

SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content

Apurva Gandhi, Ryan Serrao, Biyi Fang, Gilbert Antonius, Jenna Hong, Tra My Nguyen +4
EMNLP 2022industry

We present SLATE, a sequence labeling approach for extracting tasks from free-form content such as digitally handwritten (or “inked”) notes on a virtual whiteboard. Our approach allows us to create a single, low-latency model to simultaneously perform sentence segmentation and classification of thes…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗