Alert button
Picture for Xiaoman Pan

Xiaoman Pan

Alert button

Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models

Add code
Bookmark button
Alert button
Feb 27, 2024
Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Tongshuang Wu, Jianshu Chen

Figure 1 for Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
Figure 2 for Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
Figure 3 for Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
Figure 4 for Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
Viaarxiv icon

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Add code
Bookmark button
Alert button
Feb 25, 2024
Rui Yang, Xiaoman Pan, Feng Luo, Shuang Qiu, Han Zhong, Dong Yu, Jianshu Chen

Viaarxiv icon

Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention

Add code
Bookmark button
Alert button
Dec 14, 2023
Kaiqiang Song, Xiaoyang Wang, Sangwoo Cho, Xiaoman Pan, Dong Yu

Viaarxiv icon

Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models

Add code
Bookmark button
Alert button
Nov 15, 2023
Wenhao Yu, Hongming Zhang, Xiaoman Pan, Kaixin Ma, Hongwei Wang, Dong Yu

Viaarxiv icon

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning

Add code
Bookmark button
Alert button
Sep 30, 2023
Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu

Figure 1 for From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
Figure 2 for From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
Figure 3 for From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
Figure 4 for From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
Viaarxiv icon

LASER: LLM Agent with State-Space Exploration for Web Navigation

Add code
Bookmark button
Alert button
Sep 15, 2023
Kaixin Ma, Hongming Zhang, Hongwei Wang, Xiaoman Pan, Dong Yu

Viaarxiv icon

Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models

Add code
Bookmark button
Alert button
Aug 14, 2023
Jiaao Chen, Xiaoman Pan, Dian Yu, Kaiqiang Song, Xiaoyang Wang, Dong Yu, Jianshu Chen

Figure 1 for Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
Figure 2 for Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
Figure 3 for Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
Figure 4 for Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
Viaarxiv icon

Thrust: Adaptively Propels Large Language Models with External Knowledge

Add code
Bookmark button
Alert button
Jul 19, 2023
Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Jianshu Chen

Figure 1 for Thrust: Adaptively Propels Large Language Models with External Knowledge
Figure 2 for Thrust: Adaptively Propels Large Language Models with External Knowledge
Figure 3 for Thrust: Adaptively Propels Large Language Models with External Knowledge
Figure 4 for Thrust: Adaptively Propels Large Language Models with External Knowledge
Viaarxiv icon

MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning

Add code
Bookmark button
Alert button
Jul 16, 2023
Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu

Figure 1 for MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Figure 2 for MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Figure 3 for MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Figure 4 for MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Viaarxiv icon

PIVOINE: Instruction Tuning for Open-world Information Extraction

Add code
Bookmark button
Alert button
May 24, 2023
Keming Lu, Xiaoman Pan, Kaiqiang Song, Hongming Zhang, Dong Yu, Jianshu Chen

Figure 1 for PIVOINE: Instruction Tuning for Open-world Information Extraction
Figure 2 for PIVOINE: Instruction Tuning for Open-world Information Extraction
Figure 3 for PIVOINE: Instruction Tuning for Open-world Information Extraction
Figure 4 for PIVOINE: Instruction Tuning for Open-world Information Extraction
Viaarxiv icon