Picture for Hwee Tou Ng

Hwee Tou Ng

DSO National Laboratories

Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning

Nov 16, 2023
Figure 1 for Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Figure 2 for Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Figure 3 for Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Figure 4 for Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Viaarxiv icon

On the Robustness of Question Rewriting Systems to Questions of Varying Hardness

Add code
Nov 12, 2023
Viaarxiv icon

System Combination via Quality Estimation for Grammatical Error Correction

Add code
Oct 23, 2023
Viaarxiv icon

Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models

Add code
Jun 27, 2023
Figure 1 for Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
Figure 2 for Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
Figure 3 for Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
Figure 4 for Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
Viaarxiv icon

Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data

Add code
Jun 16, 2023
Figure 1 for Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
Figure 2 for Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
Figure 3 for Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
Figure 4 for Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
Viaarxiv icon

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

Add code
Jun 11, 2023
Figure 1 for Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Figure 2 for Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Figure 3 for Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Figure 4 for Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Viaarxiv icon

Unlocking Temporal Question Answering for Large Language Models Using Code Execution

Add code
May 24, 2023
Figure 1 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 2 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 3 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 4 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Viaarxiv icon

Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study

Add code
Feb 09, 2023
Figure 1 for Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Figure 2 for Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Figure 3 for Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Figure 4 for Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Viaarxiv icon

Grammatical Error Correction: A Survey of the State of the Art

Add code
Nov 16, 2022
Figure 1 for Grammatical Error Correction: A Survey of the State of the Art
Figure 2 for Grammatical Error Correction: A Survey of the State of the Art
Figure 3 for Grammatical Error Correction: A Survey of the State of the Art
Figure 4 for Grammatical Error Correction: A Survey of the State of the Art
Viaarxiv icon

Revisiting DocRED -- Addressing the Overlooked False Negative Problem in Relation Extraction

Add code
May 25, 2022
Figure 1 for Revisiting DocRED -- Addressing the Overlooked False Negative Problem in Relation Extraction
Figure 2 for Revisiting DocRED -- Addressing the Overlooked False Negative Problem in Relation Extraction
Figure 3 for Revisiting DocRED -- Addressing the Overlooked False Negative Problem in Relation Extraction
Figure 4 for Revisiting DocRED -- Addressing the Overlooked False Negative Problem in Relation Extraction
Viaarxiv icon