Papers by Saurav Manchanda
Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification (2024.findings-emnlp)
Copied to clipboard
Zeren Shui, Petros Karypis, Daniel Karls, Mingjian Wen, Saurav Manchanda, Ellad Tadmor, George Karypis
| Challenge: | Prior research has shown that pretrained language models (PLMs) can achieve state-of-the-art performance on CIC benchmarks. |
| Approach: | They propose a multi-task learning framework that fine-tunes pretrained language models on a dataset of primary interest together with multiple auxiliary CIC datasets to take advantage of additional supervision signals. |
| Outcome: | The proposed framework outperforms current state-of-the-art models on small datasets while aligning with the best-performing model on a large dataset. |
Uncovering Currency Bias and Syntax Gap in Text Embedding Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-embedding models often inherit societal biases, yet the influence of socio-economic markers remains unexplored. |
| Approach: | They propose to identify Currency Bias as a systemic representational limitation in financial AI . they analyze currency embeddings to identify currency identifiers and associative sensitivity . |
| Outcome: | The proposed model lacks associative sensitivity to economic hierarchies, the authors show . they show that current embedding practices pose significant risks for the fairness and reliability of financial NLP applications. |
Evaluating Scholarly Impact: Towards Content-Aware Bibliometrics (2021.emnlp-main)
Copied to clipboard
| Challenge: | Scientific, engineering, and technological (SET) innovations drive many positive advances in our modern economy, society, and life. |
| Approach: | They propose a new metric that uses the content of the paper as a source of distant-supervision to quantify how much the cited-node informs the citing-n node. |
| Outcome: | The proposed method achieves up to 103% improvement over the second-best method. |
Fooling the Textual Fooler via Randomizing Latent Representations (2024.findings-acl)
Copied to clipboard
| Challenge: | Several adversarial attacks can compromise the model without accessing the model architecture or model parameters (i.e., a blackbox setting) Several studies have revealed that deep NLP models are vulnerable to adversarials that slightly perturb the input to cause the models to misbehave. |
| Approach: | They propose a lightweight and attack-agnostic defense that perplexes the process of generating an adversarial example in query-based black-box attacks. |
| Outcome: | The proposed defense is lightweight and attack-agnostic and does not necessitate additional computational overhead during training nor does it rely on assumptions about the potential adversarial perturbation set while having a negligible impact on the model’s accuracy. |