Picture for Ben Zhou

Ben Zhou

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection

Add code
Mar 14, 2025
Viaarxiv icon

Self-supervised Analogical Learning using Language Models

Add code
Feb 03, 2025
Viaarxiv icon

ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning

Add code
Oct 24, 2024
Figure 1 for ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
Figure 2 for ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
Viaarxiv icon

ToW: Thoughts of Words Improve Reasoning in Large Language Models

Add code
Oct 21, 2024
Figure 1 for ToW: Thoughts of Words Improve Reasoning in Large Language Models
Figure 2 for ToW: Thoughts of Words Improve Reasoning in Large Language Models
Figure 3 for ToW: Thoughts of Words Improve Reasoning in Large Language Models
Figure 4 for ToW: Thoughts of Words Improve Reasoning in Large Language Models
Viaarxiv icon

FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation

Add code
Jun 17, 2024
Figure 1 for FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
Figure 2 for FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
Figure 3 for FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
Figure 4 for FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
Viaarxiv icon

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Add code
Apr 18, 2024
Figure 1 for BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
Figure 2 for BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
Figure 3 for BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
Figure 4 for BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
Viaarxiv icon

Conceptual and Unbiased Reasoning in Language Models

Add code
Mar 30, 2024
Viaarxiv icon

Deceiving Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?

Add code
Nov 16, 2023
Viaarxiv icon

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Add code
Nov 16, 2023
Figure 1 for Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Figure 2 for Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Figure 3 for Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Figure 4 for Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Viaarxiv icon

Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations

Add code
Nov 07, 2023
Viaarxiv icon