Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking · HackerPapers discussions

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by ValentinA23

Mon, 16 Sep 2024 13:27:09 GMT

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking https://arxiv.org/pdf/2403.09629 > In the Self-Taught Reasoner (STaR, Zelikman et al. 2022), useful thinking is learned by inferring rationales from few-shot examples in question-answering and learning from those that lead to a correct answer. This is a highly constrained setting – ideally, a language model could instead learn to infer unstated rationales in arbitrary text. We present Quiet-STaR, a generalization of STaR in which LMs learn to generate rationales at each token to explain future text, improving their…

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by ValentinA23

Fri, 13 Sep 2024 09:58:58 GMT

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking https://arxiv.org/abs/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by imtringued

Sun, 01 Sep 2024 09:02:53 GMT

It is in reference to this: https://arxiv.org/abs/2203.14465 https://arxiv.org/abs/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by trashtester

Wed, 28 Aug 2024 10:37:57 GMT

The specifics are kept secret, but all the labs appear to work on some variant. It seems to be related to the DeepMind reference in [1] and most of [2]. [1] https://en.wikipedia.org/wiki/Q-learning [2] https://arxiv.org/pdf/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by FeepingCreature

Sun, 12 May 2024 11:48:01 GMT

Saying that LLMs should be able to do problems without CoT is a bit like saying that humans should be able to write programs without thinking though. CoT is fundamentally an architectural necessity owed to the finite cognitive effort possible per token. Let it be CoT, let it be QuietSTaR ( https://arxiv.org/abs/2403.09629 ), let it be pause tokens ( https://arxiv.org/abs/2310.02226 ), let it even be dots ( https://arxiv.org/abs/2404.15758 ), but the thinking has to happen somewhere. I think mostly, LLMs at the moment are incredibly uneven. LLM assistants can pull obscure knowledge out of…

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by rfdearborn

Mon, 08 Apr 2024 01:31:49 GMT

The trendline is definitely toward increasing dynamic routing, but I suspect it's more so that MoE/MoD/MoDE enable models to embed additional facts with less superposition within their weights than enable deeper reasoning. Instead I expect deeper reasoning will come through token-wise dynamism rather than layer-wise -- e.g., this recent Quiet-STaR paper in which the model outputs throwaway rationale tokens: https://arxiv.org/abs/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by snats

Fri, 29 Mar 2024 20:15:09 GMT

It's been pretty interesting to see some research trying to solve this. For example, Stanford researchers recently published QuietSTaR[1]. This makes LLMs "think" before they speak. By generating a chain of thoughts and just choosing the best possible path from the generated thoughts. This method is better than Chain of Thought and I think is a step in the right direction. [1] https://arxiv.org/abs/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by mycall

Sat, 23 Mar 2024 03:31:28 GMT

Does Quiet STaR [0] address the association issue, forward reasoning using past learning? [0] https://arxiv.org/abs/2403.09629

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — mentioned by visarga

Fri, 22 Mar 2024 09:15:37 GMT

> Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking This paper suggests that a large language model should "think ahead" by predicting not only the next token but also a "supporting thought." The approach involves generating all tokens simultaneously, allowing for a single forward pass that produces both the next token and a supporting thought, which might consist of, for example, 16 tokens. This supporting thought influences the model's prediction. The process is then extended to multiple supporting thoughts by ingeniously masking cross-attention between thoughts to…

Paper and discussion history. A mention is not an endorsement.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — HN submission

Fri, 15 Mar 2024 09:24:50 GMT

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

280 points; 264 discussion replies on HN. Paper and source history. A submission is not an endorsement.