Picture for Haitao Mi

Haitao Mi

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Add code
Jun 30, 2024
Viaarxiv icon

LiteSearch: Efficacious Tree Search for LLM

Add code
Jun 29, 2024
Figure 1 for LiteSearch: Efficacious Tree Search for LLM
Figure 2 for LiteSearch: Efficacious Tree Search for LLM
Figure 3 for LiteSearch: Efficacious Tree Search for LLM
Figure 4 for LiteSearch: Efficacious Tree Search for LLM
Viaarxiv icon

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Add code
Jun 28, 2024
Figure 1 for Scaling Synthetic Data Creation with 1,000,000,000 Personas
Figure 2 for Scaling Synthetic Data Creation with 1,000,000,000 Personas
Figure 3 for Scaling Synthetic Data Creation with 1,000,000,000 Personas
Figure 4 for Scaling Synthetic Data Creation with 1,000,000,000 Personas
Viaarxiv icon

Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

Add code
Jun 11, 2024
Figure 1 for Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Figure 2 for Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Figure 3 for Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Figure 4 for Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Viaarxiv icon

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Add code
Apr 18, 2024
Figure 1 for Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Figure 2 for Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Figure 3 for Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Figure 4 for Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Viaarxiv icon

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models

Add code
Apr 14, 2024
Figure 1 for Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Figure 2 for Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Figure 3 for Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Figure 4 for Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Viaarxiv icon

Self-Consistency Boosts Calibration for Math Reasoning

Add code
Mar 14, 2024
Figure 1 for Self-Consistency Boosts Calibration for Math Reasoning
Figure 2 for Self-Consistency Boosts Calibration for Math Reasoning
Figure 3 for Self-Consistency Boosts Calibration for Math Reasoning
Figure 4 for Self-Consistency Boosts Calibration for Math Reasoning
Viaarxiv icon

A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation

Add code
Mar 06, 2024
Figure 1 for A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Figure 2 for A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Figure 3 for A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Figure 4 for A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Viaarxiv icon

Collaborative decoding of critical tokens for boosting factuality of large language models

Add code
Feb 28, 2024
Viaarxiv icon

Fine-Grained Self-Endorsement Improves Factuality and Reasoning

Add code
Feb 23, 2024
Figure 1 for Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Figure 2 for Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Figure 3 for Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Figure 4 for Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Viaarxiv icon