Picture for Pinzhen Chen

Pinzhen Chen

Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning

Add code
Feb 21, 2025
Viaarxiv icon

Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models

Add code
Oct 04, 2024
Viaarxiv icon

EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models

Add code
Sep 26, 2024
Figure 1 for EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Figure 2 for EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Figure 3 for EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Figure 4 for EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Viaarxiv icon

Pitfalls and Outlooks in Using COMET

Add code
Sep 02, 2024
Figure 1 for Pitfalls and Outlooks in Using COMET
Figure 2 for Pitfalls and Outlooks in Using COMET
Figure 3 for Pitfalls and Outlooks in Using COMET
Figure 4 for Pitfalls and Outlooks in Using COMET
Viaarxiv icon

Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation

Add code
Aug 23, 2024
Viaarxiv icon

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?

Add code
Jun 18, 2024
Viaarxiv icon

Crossmodal ASR Error Correction with Discrete Speech Units

Add code
May 26, 2024
Figure 1 for Crossmodal ASR Error Correction with Discrete Speech Units
Figure 2 for Crossmodal ASR Error Correction with Discrete Speech Units
Figure 3 for Crossmodal ASR Error Correction with Discrete Speech Units
Figure 4 for Crossmodal ASR Error Correction with Discrete Speech Units
Viaarxiv icon

Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?

Add code
Apr 22, 2024
Viaarxiv icon

Lucky 52: How Many Languages Are Needed to Instruction Fine-Tune Large Language Models?

Add code
Apr 07, 2024
Viaarxiv icon

UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing

Add code
Apr 01, 2024
Figure 1 for UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
Figure 2 for UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
Figure 3 for UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
Figure 4 for UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
Viaarxiv icon