7 citations · 16 across the 12 of their papers we have counts for
13 papers
Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation
Shreya Rajpal, Sonia Sharma, Swapnil Parekh +4
Recommender systems learn from observed user-item interactions, but explicit negative feedback is often unavailable. Since deep learning models require negative signals for trainin…
From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender
Sonia Sharma, Jeyendran Balakrishnan, Shreya Rajpal +3
Product catalogs in fast-moving service businesses are shifting from static, independently priced SKUs toward dynamically bundled, discount-coupled offerings--a shift that strains…
CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models
Swapnil Parekh
Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples. The contamination is invisible to every output-level defense: harmful behavior li…
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
Swapnil Parekh, Naman Goyal
Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberative-looking steps that contribute nothing…
Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
Swapnil Parekh
A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally…
CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
Swapnil Parekh
Every mechanistic circuit carries an invisible asterisk: it reflects not just the model's computation, but the analyst's choice of pruning threshold. Change that choice and the cir…
ACES: Accent Subspaces for Coupling, Explanations, and Stress-Testing in Automatic Speech Recognition
Swapnil Parekh
ASR systems exhibit persistent performance disparities across accents, but whether these gaps reflect superficial biases or deep structural vulnerabilities remains unclear. We intr…
CaptionFool: Universal Image Captioning Model Attacks
Swapnil Parekh
Image captioning models are encoder-decoder architectures trained on large-scale image-text datasets, making them susceptible to adversarial attacks. We present CaptionFool, a nove…
Attacking Compressed Vision Transformers
Swapnil Parekh, Devansh Shah, Pratyush Shukla
Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a…
LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents
Debanjan Mahata, Navneet Agarwal, Dibya Gautam +5
Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this ta…
AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses
Yaman Kumar Singla, Swapnil Parekh, Somesh Singh +3
Deep-learning based Automatic Essay Scoring (AES) systems are being actively used by states and language testing agencies alike to evaluate millions of candidates for life-changing…
MINIMAL: Mining Models for Data Free Universal Adversarial Triggers
Swapnil Parekh, Yaman Singla Kumar, Somesh Singh +3
It is well known that natural language models are vulnerable to adversarial attacks, which are mostly input-specific in nature. Recently, it has been shown that there also exist in…
My Teacher Thinks The World Is Flat! Interpreting Automatic Essay Scoring Mechanism
Swapnil Parekh, Yaman Kumar Singla, Changyou Chen +2
Significant progress has been made in deep-learning based Automatic Essay Scoring (AES) systems in the past two decades. However, little research has been put to understand and int…