Papers by Sriram Ganapathy
FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for trust assessment of multimodal large language models generate mispredictions due to multimodal input paradigms. |
| Approach: | They propose a multimodal input sampling technique that generates an uncertainty measure based on equivalent and complementary input samplings. |
| Outcome: | The proposed technique improves selective prediction performance with visual and audio reasoning tasks. |
Self-Influence Guided Data Reweighting for Language Model Pre-training (2023.emnlp-main)
Copied to clipboard
| Challenge: | Language Models (LMs) pre-trained with selfsupervision on large text data are the default starting point for developing models for various downstream tasks. |
| Approach: | They propose a method for jointly reweighting samples by leveraging self-influence scores as an indicator of sample importance and pre-training. |
| Outcome: | The proposed method promotes novelty and stability for model pre-training. |
Accented Speech Recognition With Accent-specific Codebooks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Degradation in performance across underrepresented accents is a severe deterrent to inclusive adoption of ASR. |
| Approach: | They propose an approach to adapt speech accents to unseen accents by using cross-attention with a trainable set of codebooks. |
| Outcome: | The proposed approach yields significant performance gains on the seen English accents and unseen accents on the Mozilla Common Voice dataset. |