activity
20192026
most citedFedSynth: Gradient Compression via Synthetic Data in Federated Learning

18 citations · 28 across the 13 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation

Zhe Liu

Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, raising concerns about fairness…

cs.CL2023

Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble

Zhe Liu, Ozlem Kalinli

Recent research has shown that language models have a tendency to memorize rare or unique token sequences in the training corpus. After deploying a model, practitioners might be as…

cs.CL2023★ 2 cited

Contextual Biasing of Named-Entities with Large Language Models

Chuanneng Sun, Zeeshan Ahmed, Yingyi Ma +4

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automati…

cs.CL2023★ 2 cited

Recovering from Privacy-Preserving Masking with Large Language Models

Arpita Vats, Zhe Liu, Peng Su +5

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typica…

cs.CL2022

Mitigating Unintended Memorization in Language Models via Alternating Teaching

Zhe Liu, Xuedong Zhang, Fuchun Peng

Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. W…

cs.CL2022

Neural-FST Class Language Model for End-to-End Speech Recognition

Antoine Bruguier, Duc Le, Rohit Prabhavalkar +7

We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transduce…