Picture for Ke Shen

Ke Shen

SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL

Add code
Sep 16, 2024
Viaarxiv icon

Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference

Add code
Aug 04, 2024
Viaarxiv icon

An Evaluation of Estimative Uncertainty in Large Language Models

Add code
May 24, 2024
Viaarxiv icon

A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores

Add code
Oct 05, 2023
Viaarxiv icon

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

Add code
Oct 03, 2022
Figure 1 for Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes
Figure 2 for Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes
Figure 3 for Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes
Figure 4 for Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes
Viaarxiv icon

Understanding Substructures in Commonsense Relations in ConceptNet

Add code
Oct 03, 2022
Figure 1 for Understanding Substructures in Commonsense Relations in ConceptNet
Figure 2 for Understanding Substructures in Commonsense Relations in ConceptNet
Figure 3 for Understanding Substructures in Commonsense Relations in ConceptNet
Figure 4 for Understanding Substructures in Commonsense Relations in ConceptNet
Viaarxiv icon

A Theoretically Grounded Benchmark for Evaluating Machine Commonsense

Add code
Mar 23, 2022
Figure 1 for A Theoretically Grounded Benchmark for Evaluating Machine Commonsense
Figure 2 for A Theoretically Grounded Benchmark for Evaluating Machine Commonsense
Viaarxiv icon

A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base

Add code
Nov 28, 2020
Figure 1 for A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
Figure 2 for A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
Figure 3 for A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
Figure 4 for A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
Viaarxiv icon

Do Fine-tuned Commonsense Language Models Really Generalize?

Add code
Nov 18, 2020
Figure 1 for Do Fine-tuned Commonsense Language Models Really Generalize?
Figure 2 for Do Fine-tuned Commonsense Language Models Really Generalize?
Figure 3 for Do Fine-tuned Commonsense Language Models Really Generalize?
Figure 4 for Do Fine-tuned Commonsense Language Models Really Generalize?
Viaarxiv icon

Ranking sentences from product description & bullets for better search

Add code
Jul 15, 2019
Figure 1 for Ranking sentences from product description & bullets for better search
Figure 2 for Ranking sentences from product description & bullets for better search
Figure 3 for Ranking sentences from product description & bullets for better search
Figure 4 for Ranking sentences from product description & bullets for better search
Viaarxiv icon