2 citations · 5 across the 23 of their papers we have counts for
6 papers · 1 filter
Capturing In-Context Learning Dynamics with Task Operators
Guangzhi Xiong, Zhenghao He, Bohan Liu +3
In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of…
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Zhenghao He, Guangzhi Xiong, Bohan Liu +2
Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that triggers this behavior remains poorly unders…
Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
Guangzhi Xiong, Zhenghao He, Bohan Liu +2
Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generation…
MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning
Sanchit Sinha, Yuguang Yue, Victor Soto +3
Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts…
Don't Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters
Anshu Bhatia, Sanchit Sinha, Saket Dingliwal +3
Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such repr…
Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon +2
Interpretability methods like Integrated Gradient and LIME are popular choices for explaining natural language model predictions with relative word importance scores. These interpr…