Measuring Faithfulness in Chain-of-Thought Reasoning paper: https://
www-files.anthropic.com/production/fil
es/measuring-faithfulness-in-chain-of-thought-reasoning.pdf
… Large language models (LLMs) perform better when they produce step-by-step, “Chain-ofThought” (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful
RESEARCH
-
Measuring Faithfulness in Chain-of-Thought Reasoning
By
–
-
Meta releases LLaMa-2 open-weight language model free
By
–
LLaMa-2 from @MetaAI is here!
Open weights, free for research and commercial use. Pre-trained on 2T tokens.
Fine-tuned too (unlike v1). Lets gooo…. https://
ai.meta.com/llama/
The paper lists the amazing authors who worked to make this happen night and day. Be sure to thank -
Anthropic improves language model reasoning through faithful explanations
By
–
We’re excited about ways to make language models generate more faithful explanations that help them reason better! We encourage you to check out our papers for more results and details: https://
www-files.anthropic.com/production/fil
es/measuring-faithfulness-in-chain-of-thought-reasoning.pdf
… https://
www-files.anthropic.com/production/fil
es/question-decomposition-improves-the-faithfulness-of-model-generated-reasoning.pdf
… -
Anthropic Hiring Research Engineers and Scientists
By
–
If you’re excited about this kind of research, the team that led this work is actively hiring research engineers and scientists, and we’d encourage you to apply: https://
jobs.lever.co/Anthropic/436c
a148-6440-460f-b2a2-3334d9b142a5
… https://
jobs.lever.co/Anthropic/eb9e
6d83-626c-4f59-8a0e-fa7c413b2014
… -
Decomposition techniques reduce model reasoning bias
By
–
Decomposition could mitigate issues with models ignoring their reasoning by clearly specifying the relationship between reasoning steps. Answering subquestions in isolated contexts could also reduce the model’s ability to generate biased reasoning.
-
Models Rely on Decomposition-Based Reasoning Strategies
By
–
We find that models rely more on decomposition-based reasoning! Using the same metrics we propose in Lanham et al., we conclude that models change their answers more when they are forced to answer with a truncated or corrupted version of their decomposition-based reasoning.
-
Decomposition Methods Improve Reasoning Faithfulness Trade-offs
By
–
We find different methods for generating reasoning make different tradeoffs between question-answering accuracy and reasoning faithfulness. Our decomposition-based methods push the performance-faithfulness Pareto frontier, making us optimistic for further improvements.
-
Reasoning Faithfulness Decreases as AI Models Scale
By
–
We find that reasoning faithfulness shows inverse scaling: as models increase in size and capability, the faithfulness of their reasoning decreases for most tasks studied. In cases where reasoning faithfulness is important, using smaller models may help.
-
Improving Model Reasoning Through Question Decomposition Methods
By
–
To improve the faithfulness of model-generated reasoning, we study two other ways of eliciting reasoning from models in Radhakrishnan et al. These methods rely on question decomposition, or breaking down a question into smaller subquestions to help answer the original question.
-
Testing Chain of Thought Reasoning Faithfulness in AI Models
By
–
We make edits to the model’s chain of thought (CoT) reasoning to test hypotheses about how CoT reasoning may be unfaithful. For example, the model’s final answer should change when we introduce a mistake during CoT generation.