Papers by Bhiksha Raj
Token Prediction as Implicit Classification to Identify LLM-Generated Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach for identifying large language models (LLMs) involved in text generation is proposed . instead of adding an additional classification layer, we reframe the classification task as a next-token prediction task . |
| Approach: | They propose a novel approach for identifying large language models involved in text generation . instead of adding an additional classification layer, they reframe the task as a next-token prediction task . |
| Outcome: | The proposed method performs exceptionally well in the text classification task . it can distinguish distinctive writing styles among various LLMs even without an explicit classifier. |
Sequential Randomized Smoothing for Adversarially Robust Speech Recognition (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing, naive defenses against adversarial attacks are lagging . a new paper aims to break these defenses with adaptive noise ensembling . |
| Approach: | They propose a randomized smoothing paradigm that can be used to break adversarial attacks . they use speech enhancement methods and a novel use for ASR output ensembling methods . |
| Outcome: | The proposed model is robust to all attacks that use inaudible noise and can only be broken with very high distortion. |
PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Vocabulary acquisition is a challenge for second-language learners when learning typologically distant languages such as English and Korean, where phonological and structural mismatches complicate vocabulary learning. |
| Approach: | They propose a cross-lingual mnemonic generation system that performs IPA-based phonological adaptation and syllable-aware alignment to retrieve L1 keyword sequence and uses LLMs to generate verbal cues. |
| Outcome: | The proposed system outperforms human-written and automated mnemonics in a short-term recall test with human participants and achieves quality comparable to human-writing mnms. |
SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks only evaluate a subset of potential conditions, missing others entirely. |
| Approach: | a new benchmark suite evaluates speaker verification models under a variety of stressors . a san francisco-based team evaluates models under natural and background conditions . |
| Outcome: | a new benchmark suite evaluates speaker verification models under stressors under a variety of conditions . the results show that some models perform better under stress conditions than others . |
Continual Contrastive Spoken Language Understanding (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in speech processing require extensive offline training . however, these models struggle to retain their previously acquired knowledge when learning new tasks continuously. |
| Approach: | They propose a method that relies on experience replay and contrastive learning to preserve the learned representations by pulling closer samples from the same class and pushing away the others. |
| Outcome: | The proposed method preserves the learned representations by pulling closer samples from the same class and pushing away the others. |
R-BASS : Relevance-aided Block-wise Adaptation for Speech Summarization (2024.findings-naacl)
Copied to clipboard
| Challenge: | End-to-end speech summarization on long recordings is challenging because of the high computational cost. |
| Approach: | They propose a new relevance-aware block-wise adaptation method that automatically estimates block relevance based on lexical and semantic similarity between transcript and summary. |
| Outcome: | The proposed method can drop 86.3 % of blocks while maintaining comparable performance. |
Automatic In-the-wild Dataset Annotation with Deep Generalized Multiple Instance Learning (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to label large datasets that resemble real life situations are prohibitive due to the cost of manual labeling. |
| Approach: | They propose to automate the annotation process by using end-to-end differentiable neural networks to label large datasets that resemble real life conditions. |
| Outcome: | The proposed method can label a large dataset in the wild without human intervention without any cost. |
AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet relying on extensive manual labeling to provide procedural feedback remains a significant impediment. |
| Approach: | They propose a self-supervised framework that decomposes complex problems into manageable subquestions with a controllable granularity switch and sequentially applies reinforcement learning to iteratively improve the subquest solver. |
| Outcome: | The proposed framework improves performance on mathematical and commonsense reasoning tasks over SOTA. |
Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Automatic speech recognition systems have seen remarkable improvements in recent years, but evaluation of performance remains dependent on word and character error rate (WER/CER). |
| Approach: | They investigate how distribution shifts, model size and model architecture influence hallucination error rate (HER) HER is a metric used to quantify hallucinosity in automatic speech recognition systems. |
| Outcome: | The proposed model can be used to measure hallucination errors in high-stakes domains such as healthcare, legal, and aviation. |
On the Robust Approximation of ASR Metrics (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for estimating speech recognition metrics depend on ground truth labels. |
| Approach: | They propose a label-free approach to approximating ASR performance metrics . they embed multimodal embeddings in a unified space for speech and transcription representations . |
| Outcome: | The proposed method outperforms baseline models on speech recognition benchmarks by 50%. |
Towards Noise-Tolerant Speech-Referring Video Object Segmentation: Bridging Speech and Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in vision-language learning have significantly advanced Human-Computer Interactions (HCI). |
| Approach: | They propose a method to align the semantic spaces between speech and text by incorporating two modules to align semantic spaces. |
| Outcome: | The proposed method outperforms state-of-the-art approaches on AVOS benchmarks. |
CAARMA: Class Augmentation with Adversarial Mixup Regularization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Speaker verification tasks require inference of unseen classes using specialized losses. |
| Approach: | They propose a class augmentation framework that generates synthetic classes through data mixing in the embedding space. |
| Outcome: | The proposed framework improves speaker verification tasks by 8% over baseline models. |
uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent work on distilling Whisper’s knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. |
| Approach: | They propose a framework that distills Whisper’s knowledge into small models using pseudo-labels and reduces the size by up to 50%. |
| Outcome: | The proposed model outperforms the teacher model by 5-7 WER points and is 25-50% more efficient when scaling the data. |