Hugging Face's logo
Moon Lockwood's picture
2 1 14

Moon Lockwood

moonlock
·

AI & ML interests

art programming music psychology

Recent Activity

upvoted a collection about 1 month ago
DeepSeek-R1
liked a model 12 months ago
nisten/Biggie-SmoLlm-0.15B-Base
reacted to akhaliq's post with 👍 over 1 year ago
Chain-of-Thought Reasoning Without Prompting paper page: https://huggingface.co/papers/2402.10200 In enhancing the reasoning capabilities of large language models (LLMs), prior research primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of-thought (CoT) prompting. These methods, while effective, often involve manually intensive prompt engineering. Our study takes a novel approach by asking: Can LLMs reason effectively without prompting? Our findings reveal that, intriguingly, CoT reasoning paths can be elicited from pre-trained LLMs by simply altering the decoding process. Rather than conventional greedy decoding, we investigate the top-k alternative tokens, uncovering that CoT paths are frequently inherent in these sequences. This approach not only bypasses the confounders of prompting but also allows us to assess the LLMs' intrinsic reasoning abilities. Moreover, we observe that the presence of a CoT in the decoding path correlates with a higher confidence in the model's decoded answer. This confidence metric effectively differentiates between CoT and non-CoT paths. Extensive empirical studies on various reasoning benchmarks show that the proposed CoT-decoding substantially outperforms the standard greedy decoding.
View all activity

Organizations

None yet