Picture for Xiaochuang Han

Xiaochuang Han

Tuning Language Models by Proxy

Add code
Jan 16, 2024
Figure 1 for Tuning Language Models by Proxy
Figure 2 for Tuning Language Models by Proxy
Figure 3 for Tuning Language Models by Proxy
Figure 4 for Tuning Language Models by Proxy
Viaarxiv icon

What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization

Add code
Nov 16, 2023
Figure 1 for What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization
Figure 2 for What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization
Figure 3 for What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization
Figure 4 for What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization
Viaarxiv icon

On the Zero-Shot Generalization of Machine-Generated Text Detectors

Add code
Oct 08, 2023
Figure 1 for On the Zero-Shot Generalization of Machine-Generated Text Detectors
Figure 2 for On the Zero-Shot Generalization of Machine-Generated Text Detectors
Figure 3 for On the Zero-Shot Generalization of Machine-Generated Text Detectors
Figure 4 for On the Zero-Shot Generalization of Machine-Generated Text Detectors
Viaarxiv icon

In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning

Add code
Aug 08, 2023
Viaarxiv icon

Understanding In-Context Learning via Supportive Pretraining Data

Jun 26, 2023
Figure 1 for Understanding In-Context Learning via Supportive Pretraining Data
Figure 2 for Understanding In-Context Learning via Supportive Pretraining Data
Figure 3 for Understanding In-Context Learning via Supportive Pretraining Data
Figure 4 for Understanding In-Context Learning via Supportive Pretraining Data
Viaarxiv icon

SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models

Add code
May 24, 2023
Figure 1 for SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models
Figure 2 for SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models
Figure 3 for SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models
Figure 4 for SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models
Viaarxiv icon

Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

May 24, 2023
Figure 1 for Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
Figure 2 for Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
Figure 3 for Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
Figure 4 for Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
Viaarxiv icon

Can Language Models Solve Graph Problems in Natural Language?

Add code
May 17, 2023
Figure 1 for Can Language Models Solve Graph Problems in Natural Language?
Figure 2 for Can Language Models Solve Graph Problems in Natural Language?
Figure 3 for Can Language Models Solve Graph Problems in Natural Language?
Figure 4 for Can Language Models Solve Graph Problems in Natural Language?
Viaarxiv icon

Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?

Dec 20, 2022
Figure 1 for Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
Figure 2 for Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
Figure 3 for Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
Figure 4 for Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
Viaarxiv icon

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

Add code
Oct 31, 2022
Figure 1 for SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Figure 2 for SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Figure 3 for SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Figure 4 for SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Viaarxiv icon