Picture for Can Zu

Can Zu

Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution

Feb 27, 2024
Viaarxiv icon

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration

Add code
Feb 18, 2024
Viaarxiv icon

InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction

Add code
Apr 17, 2023
Figure 1 for InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Figure 2 for InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Figure 3 for InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Figure 4 for InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Viaarxiv icon

A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Add code
Mar 18, 2023
Figure 1 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 2 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 3 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 4 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Viaarxiv icon

How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks

Mar 01, 2023
Figure 1 for How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Figure 2 for How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Figure 3 for How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Figure 4 for How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Viaarxiv icon