Faithful Chain of Thought
Published:
Faithful Chain-of-Thought Reasoning
This post is an overview of the paper: Faithful Chain-of-Thought Reasoning by Lyu, Havaldar, Stein et al. The paper is linked here: https://arxiv.org/pdf/2310.15164
Posts by Category
CoT
LLM
Reinforcement learning for NLP
Published:
In my last post, I talked about applying an originally image-based machine learning method to language, and the challenges that came with it. Today, we’re going to be discussing a similar topic—specifically, Reinforcement Learning (RL) for NLP reasoning. Though not initially used for LLMs, RL has a number of benefits when applied to LLMs. Specifically, RL allows LLMs to learn how to create outputs with specific goals in mind.
Diffusion in language models, and rethinking thought
Published:
Diffusion in language models, and rethinking thought
Dissociating Language and Thought in LLMs
Published:
Dissociating Language and Thought in LLMs
This post is an overview of the paper: Dissociating Language and Thought in Large Language Models: A Cognitive Perspective by Mahowald and Ivanova et al. The paper is linked here: https://arxiv.org/abs/2301.06627
Faithful Chain of Thought
Published:
Faithful Chain-of-Thought Reasoning
This post is an overview of the paper: Faithful Chain-of-Thought Reasoning by Lyu, Havaldar, Stein et al. The paper is linked here: https://arxiv.org/pdf/2310.15164
LINC: Neurosymbolic reasoning approach for LLM
Published:
LINC: Neurosymbolic Reasoning for LLMs
This post is an overview of the paper: LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers by Olausson et al. The paper is linked here: https://arxiv.org/pdf/2310.15164
The LLM Reversal Curse
Published:
Paper Overview: The LLM Reversal Curse
cognitive science
Dissociating Language and Thought in LLMs
Published:
Dissociating Language and Thought in LLMs
This post is an overview of the paper: Dissociating Language and Thought in Large Language Models: A Cognitive Perspective by Mahowald and Ivanova et al. The paper is linked here: https://arxiv.org/abs/2301.06627
diffusion
Diffusion in language models, and rethinking thought
Published:
Diffusion in language models, and rethinking thought
linguistics
Dissociating Language and Thought in LLMs
Published:
Dissociating Language and Thought in LLMs
This post is an overview of the paper: Dissociating Language and Thought in Large Language Models: A Cognitive Perspective by Mahowald and Ivanova et al. The paper is linked here: https://arxiv.org/abs/2301.06627
reasoning
Faithful Chain of Thought
Published:
Faithful Chain-of-Thought Reasoning
This post is an overview of the paper: Faithful Chain-of-Thought Reasoning by Lyu, Havaldar, Stein et al. The paper is linked here: https://arxiv.org/pdf/2310.15164
LINC: Neurosymbolic reasoning approach for LLM
Published:
LINC: Neurosymbolic Reasoning for LLMs
This post is an overview of the paper: LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers by Olausson et al. The paper is linked here: https://arxiv.org/pdf/2310.15164
The LLM Reversal Curse
Published:
Paper Overview: The LLM Reversal Curse
reinforcement learning
Reinforcement learning for NLP
Published:
In my last post, I talked about applying an originally image-based machine learning method to language, and the challenges that came with it. Today, we’re going to be discussing a similar topic—specifically, Reinforcement Learning (RL) for NLP reasoning. Though not initially used for LLMs, RL has a number of benefits when applied to LLMs. Specifically, RL allows LLMs to learn how to create outputs with specific goals in mind.
thought
Diffusion in language models, and rethinking thought
Published: