Picture for Boxin Wang

Boxin Wang

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs

Add code
Jul 02, 2024
Viaarxiv icon

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Add code
Oct 11, 2023
Figure 1 for InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Figure 2 for InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Figure 3 for InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Figure 4 for InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Viaarxiv icon

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Add code
Jun 20, 2023
Figure 1 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 2 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 3 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 4 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Viaarxiv icon

Can Public Large Language Models Help Private Cross-device Federated Learning?

Add code
May 20, 2023
Figure 1 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 2 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 3 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 4 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Viaarxiv icon

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study

Add code
Apr 13, 2023
Figure 1 for Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Figure 2 for Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Figure 3 for Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Figure 4 for Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Viaarxiv icon

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data

Add code
Jul 21, 2022
Figure 1 for FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
Figure 2 for FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
Viaarxiv icon

SemAttack: Natural Textual Attacks via Different Semantic Spaces

Add code
May 16, 2022
Figure 1 for SemAttack: Natural Textual Attacks via Different Semantic Spaces
Figure 2 for SemAttack: Natural Textual Attacks via Different Semantic Spaces
Figure 3 for SemAttack: Natural Textual Attacks via Different Semantic Spaces
Figure 4 for SemAttack: Natural Textual Attacks via Different Semantic Spaces
Viaarxiv icon

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Add code
Feb 08, 2022
Figure 1 for Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Figure 2 for Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Figure 3 for Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Figure 4 for Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Viaarxiv icon

Certifying Out-of-Domain Generalization for Blackbox Functions

Add code
Feb 03, 2022
Figure 1 for Certifying Out-of-Domain Generalization for Blackbox Functions
Figure 2 for Certifying Out-of-Domain Generalization for Blackbox Functions
Figure 3 for Certifying Out-of-Domain Generalization for Blackbox Functions
Figure 4 for Certifying Out-of-Domain Generalization for Blackbox Functions
Viaarxiv icon

Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

Add code
Nov 04, 2021
Figure 1 for Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Figure 2 for Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Figure 3 for Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Figure 4 for Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Viaarxiv icon