22 citations · 54 across the 23 of their papers we have counts for
5 papers · 2 filters
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases
Rishabh Bhardwaj, Soujanya Poria
Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful ag…
Adapter Pruning using Tropical Characterization
Rishabh Bhardwaj, Tushar Vaidya, Soujanya Poria
Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained languag…
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Rishabh Bhardwaj, Soujanya Poria
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emerg…
ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation
Pengfei Hong, Rishabh Bhardwaj, Navonil Majumdar +2
Domain shift is a big challenge in NLP, thus, many approaches resort to learning domain-invariant features to mitigate the inference phase domain shift. Such methods, however, fail…
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding
Yingting Li, Ambuj Mehrish, Shuai Zhao +5
Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the…