Picture for Aaron Chan

Aaron Chan

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Feb 22, 2024
Figure 1 for Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
Figure 2 for Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
Figure 3 for Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
Figure 4 for Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
Viaarxiv icon

Tailoring Self-Rationalizers with Multi-Reward Distillation

Add code
Nov 06, 2023
Viaarxiv icon

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

Oct 07, 2023
Figure 1 for Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
Figure 2 for Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
Figure 3 for Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
Figure 4 for Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
Viaarxiv icon

Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales

Add code
May 11, 2023
Figure 1 for Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Figure 2 for Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Figure 3 for Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Figure 4 for Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Viaarxiv icon

KNIFE: Knowledge Distillation with Free-Text Rationales

Dec 19, 2022
Figure 1 for KNIFE: Knowledge Distillation with Free-Text Rationales
Figure 2 for KNIFE: Knowledge Distillation with Free-Text Rationales
Figure 3 for KNIFE: Knowledge Distillation with Free-Text Rationales
Figure 4 for KNIFE: Knowledge Distillation with Free-Text Rationales
Viaarxiv icon

PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

Add code
Nov 03, 2022
Figure 1 for PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Figure 2 for PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Figure 3 for PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Figure 4 for PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Viaarxiv icon

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

Oct 30, 2022
Figure 1 for XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Figure 2 for XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Figure 3 for XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Figure 4 for XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Viaarxiv icon

FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

Jul 02, 2022
Figure 1 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales
Figure 2 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales
Figure 3 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales
Figure 4 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales
Viaarxiv icon

ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

Add code
May 25, 2022
Figure 1 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models
Figure 2 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models
Figure 3 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models
Figure 4 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models
Viaarxiv icon

UniREx: A Unified Learning Framework for Language Model Rationale Extraction

Add code
Dec 16, 2021
Figure 1 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction
Figure 2 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction
Figure 3 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction
Figure 4 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction
Viaarxiv icon