Picture for Wenda Xu

Wenda Xu

BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM

Jun 18, 2024
Viaarxiv icon

Perils of Self-Feedback: Self-Bias Amplifies in Large Language Models

Feb 18, 2024
Viaarxiv icon

Pinpoint, Not Criticize: Refining Large Language Models via Fine-Grained Actionable Feedback

Add code
Nov 15, 2023
Viaarxiv icon

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Add code
Aug 06, 2023
Figure 1 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 2 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 3 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 4 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Viaarxiv icon

INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback

Add code
May 23, 2023
Figure 1 for INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
Figure 2 for INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
Figure 3 for INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
Figure 4 for INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
Viaarxiv icon

CausalDialogue: Modeling Utterance-level Causality in Conversations

Add code
Dec 20, 2022
Figure 1 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 2 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 3 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 4 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Viaarxiv icon

SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation

Add code
Dec 19, 2022
Figure 1 for SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation
Figure 2 for SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation
Figure 3 for SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation
Figure 4 for SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation
Viaarxiv icon

Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis

Add code
Oct 10, 2022
Figure 1 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 2 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 3 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 4 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Viaarxiv icon

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

Add code
Oct 07, 2022
Figure 1 for Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Figure 2 for Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Figure 3 for Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Figure 4 for Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Viaarxiv icon

Anticipating the Unseen Discrepancy for Vision and Language Navigation

Sep 10, 2022
Figure 1 for Anticipating the Unseen Discrepancy for Vision and Language Navigation
Figure 2 for Anticipating the Unseen Discrepancy for Vision and Language Navigation
Figure 3 for Anticipating the Unseen Discrepancy for Vision and Language Navigation
Figure 4 for Anticipating the Unseen Discrepancy for Vision and Language Navigation
Viaarxiv icon