Chain-of-Thought Prompting Elicits Reasoning in Large Language Models · HackerPapers discussions

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by minimaxir

Thu, 03 Sep 2026 20:18:14 GMT

"Chain of Thoughts" is a term from the title of a 2022 research paper "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models" (https://arxiv.org/abs/2201.11903), well before ChatGPT and the subsequent marketing hype. If anything, it's the most correct way to use the term.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by jfyi

Fri, 14 Aug 2026 12:27:06 GMT

Jason Wei's chain-of-thought prompting techniques literally revolutionized llms themselves. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by jurgenburgen

Sat, 01 Aug 2026 09:22:08 GMT

Reasoning improves the output of the model. Originally it was a prompting method called chain of thought but later models were trained to do the reasoning steps without the human prompting for it. Being able to see the reasoning steps is just an accidental benefit. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by isomorphic_duck

Wed, 17 Jun 2026 06:44:40 GMT

My biggest gripe with the discourse around AI, especially by programmers with hubris about Machine Learning, is the idea that LLMs can’t come up with “novel solutions”. They can, and they have. CoT[0] is how LLMs can output tokens in “reasoning space” to guide their “thinking” to produce absolutely novel solutions. You can imagine reasoning being multi-layered, where the top layer is an abstract heuristic (examples of which can be “try special cases”, “try solving a part of the problem with relaxed constraints”). The lower layers become more and more concrete with the details of the problem…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by choppaface

Mon, 04 May 2026 13:09:33 GMT

Isn’t this sort of just “chain of thought” (i.e. the seminal https://arxiv.org/abs/2201.11903 ) where the user is helping the model 1-shot or k-shot the solution instead of 0-shot? I’ve used a similar technique to great effect. I feel things are so new / moving so fast that it’s hard to have common lingo. So very helpful to have a blog / example! But I wonder if the phenomena has been seen / understood before and just in smaller circles / different name.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by password54321

Sat, 21 Feb 2026 13:08:00 GMT

AI from first principles has not changed. Fundamentally it is: neural nets, transformers and RL. The most important paper in recent years is on CoT [https://arxiv.org/pdf/2201.11903] and I'm not even sure what comes close. And I think what's more important these days is knowing how to filter the noise from the signal. This is probably one of the better blogs I have read recently that shows the general direction currently in AI which are improvements on the generator / verifier loop: https://www.julian.ac/blog/2025/11/13/alphaproof-paper/

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by cubefox

Wed, 08 Oct 2025 20:24:09 GMT

Yeah. One example of people mindlessly mass citing some random paper is this: Chain of thought (CoT) prompting was used in the past to greatly enhance the reasoning ability of LLMs. Usually this paper is cited when CoT is discussed: https://arxiv.org/abs/2201.11903 It has over 20,000 citations according to Google Scholar. But clearly the technique was not invented by these authors. It was known 1.5 years earlier, just after GPT-3 came out: https://xcancel.com/kleptid/status/1284069270603866113#m Perhaps even longer. But the paper above is cited nonetheless. Probably because there is pressure…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by KTibow

Sat, 24 May 2025 22:49:06 GMT

I'm not much of an ML engineer but I can point you to the original chain of thought paper [0] and Anthropic's docs on how to enable their official thinking scratchpad [1]. [0] https://arxiv.org/pdf/2201.11903 [1] https://docs.anthropic.com/en/docs/build-with-claude/extende...

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by Kubuxu

Sun, 26 Jan 2025 11:22:50 GMT

Chain of Thought was known since 2022 (https://arxiv.org/abs/2201.11903), we just were stuck in a world where we were dumping more data and compute at the training instead of looking at other improvements.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — HN submission

Wed, 15 Jan 2025 15:29:12 GMT

Show HN: QwQ-32B APIs – o1 like reasoning at 1% the cost

Ubicloud is an open source alternative to AWS. Today, we launched our inference APIs, built with open source AI models. QwQ-32B-Preview is one of those models; and it can provide o1-like reasoning at 1% the cost. QwQ is licensed under Apache 2.0 [1] and Ubicloud under AGPL v3. We deploy open models on a cloud stack that can run anywhere. This allows us to offer great price / performance. From an accuracy standpoint, QwQ does well in math and coding domains. For example, in the MMLU-Pro Computer Science LLM Benchmark, the accuracy rankings are as follows. Claude-3.5 Sonnet (82.5)…

17 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by tannhaeuser

Sat, 19 Oct 2024 07:49:45 GMT

Of course Prolog is no magic but I'm sure you know the argument in favor of having LLMs generate Prolog are based on the observation that prompting or otherwise making an LLM to perform chain-of-thought reasoning results in demonstratable experimental improvements, with [1] the canonical paper, and using Prolog with its unique characteristics and roots in NLP and logic an extension of that idea termed program-as-thought. OpenAI's latest o1 model makes heavy use of CoD internally until it returns an answer to the user. [1]: https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by burntcaramel

Thu, 17 Oct 2024 23:56:09 GMT

COT = Chain-of-Thought https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by ipsum2

Thu, 03 Oct 2024 23:32:26 GMT

No. CoT has been around for several years (Jan 2022) https://arxiv.org/abs/2201.11903. And so has Reflection (March 2023) https://arxiv.org/abs/2303.11366. This approach that was taken by Reflection is nothing new.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by danielmarkbruce

Thu, 03 Oct 2024 21:02:22 GMT

That prompts aren't science means little. If anything it makes them more important because you can't systematically arrive at good ones. If one spends a lot of time building an application to achieve an actual goal they'll realize the prompts make a gigantic difference and it takes an enormous amount of fiddly, annoying work to improve. I do this (and I built an agent system, which was more straightforward to do...) in financial markets. It so much so that people build systems just to be able to iterate on prompts (https://www.promptlayer.com/). I may be wrong - but I'll speculate you work on…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by myownpetard

Sun, 22 Sep 2024 04:17:54 GMT

> as part of/after the main training I take this to mean during weight updates, e.g. training. > "runtime train of thought" I take runtime here to mean inference, not during RL. What does runtime mean to you? Previous approaches [0] successfully used inference time chain of thought to improve model responses. That has nothing to do with RL though. The grandparent is wrong about the paper. They are doing chain of thought responses during training and doing RL on that to update the weights, not just during inference/runtime. [0] https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by seanhunter

Wed, 14 Aug 2024 10:21:44 GMT

My understanding is this used to be the case[1] but isn't really true any longer due to things like the "star" method for model training[2]. Empirically it absolutely (circa GPT3) used to be the case that if you prompted with "Explain all your reasoning step by step and then give the answer at the end" or similar it would give you a better answer for a complex question than if you said "Just give me the answer and nothing else" or similar, or asked for the answer first, and then circa gpt-4 answers started getting much longer even if you asked the model to be concise. That doesn't seem to be…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by bunderbunder

Wed, 29 May 2024 15:21:45 GMT

Justification before decision still works out better in practice, though, because of chain of thought [1]. You'll tend to get more accurate and better-justified decisions. With decision before justification, you tend to have a greater risk of the output being a wrong decision followed by convincing BS justifying it. (edit: Another way you could think of it is, LLMs still can't violate causality. Attention heads' ability to look in both directions with respect to a particular token's position in the sequence does not enable them to see into the future and observe tokens that don't exist yet.)…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by jappgar

Mon, 15 Jan 2024 18:24:10 GMT

I've found that for tasks like this you need to ask the model to output its reasoning prior to outputting the "answer". See "chain of thought" e.g https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by seanhunter

Thu, 21 Dec 2023 07:45:10 GMT

The verbosity certainly seems to me to be a specific change they have made. My guess is by getting it to do more "thinking out loud" they are trying to get it to do the kind of reasoning it used to only do when you prompted it to give its chain of thought, because that generally gives better results[1]. [1] Here's the original paper but there's lots of other research in this area. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by seanhunter

Thu, 23 Nov 2023 10:28:02 GMT

I quite agree and so would Wittgenstein, who (as I understand it) argued that precise language is essential to thought and reasoning[1]. I think one of the key things here is often what we think of as reasoning boils down to taking a problem in the real world and building a model of it using some precise language that we can then apply some set of known tools to deal with. Your example of a quadratic is perfect, because of course now I see (a) I know right away that it's an upwards-facing parabola with a line of symmetry at -5/2, that the roots are at -4 and -1 etc whereas if I saw (b) I…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by redox99

Tue, 08 Aug 2023 19:00:00 GMT

Obviously not. For example using Chain of Thought will increase the model's performance[1] [1] https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by ma2rten

Tue, 08 Aug 2023 15:50:01 GMT

I didn't have time to read this, but it is a single author paper, the author is not affiliated with a research group, it is not peer reviewed, it was published on a preprint server that I have never heard of. LLMs can definitely perform some kinds of reasoning. For example GSM8K is a dataset of grade school math problem requiring reasoning that LLMs are typically evaluated at. We talk about one method for this in our chain of thought paper [1] [1] https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by krychu

Mon, 10 Jul 2023 07:10:31 GMT

Chain of thought: https://arxiv.org/abs/2201.11903 ReAct: https://arxiv.org/abs/2210.03629 Reflexion: https://arxiv.org/abs/2303.11366 Tree of thoughts: https://arxiv.org/abs/2305.10601 Good video on "Tree of thoughts" which also reviews / puts it in the context of other methods: https://www.youtube.com/watch?v=ut5kp56wW_4 Completion vs conversational interface is something you can read about in the OpenAI API documentation. For the remaining things I don't have single specific pointer at hand.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by seanhunter

Wed, 05 Jul 2023 16:01:19 GMT

It has a specific technical connotation but it does map exactly to what you think it is.[1] Basically it's a trick that recognizes that language transformers only perform computation to generate words so for complex tasks you can get better results by asking the model to explain its chain of thought and only give the answer at the end. This has the effect of giving the model "time to think". If it didn't generate those words it wouldn't have anything to hang that computation off since it is fundamentally a word-generation model. [1] https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by ickelbawd

Wed, 05 Jul 2023 16:00:19 GMT

They’re referring to a method of prompting the model that encourages it to think through something step by step rather than spit out the answer. I think this is the paper that really kicked off this technique: https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by cosmojg

Tue, 09 May 2023 00:55:35 GMT

Just speculating, but this looks like precisely the sort of result one might expect from fine-tuning models on chain-of-thought-prompted interactions like those described by Wei et al. in 2022[1]. Alternatively, as Madaan et al. show in their 2022 paper[2], this may simply be the result of larger language models having seen more code, and thus structured reasoning, in their training data. [1] https://arxiv.org/abs/2201.11903 [2] https://arxiv.org/abs/2210.07128

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by sp332

Wed, 26 Apr 2023 19:31:02 GMT

That is important, but asking in certain ways can make a big difference. E.g. https://twitter.com/mitchellh/status/1645562198935347205. And just putting “let’s think step by step” at the end can really help some of the larger GPT models. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by famouswaffles

Tue, 11 Apr 2023 03:46:10 GMT

chain of thought prompting. It's well known https://arxiv.org/abs/2205.11916 https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by BiasRegularizer

Mon, 03 Apr 2023 15:35:38 GMT

It's not impossible to see that LLMs can make finite step "reasoning" between input and output, as each block of the transformer can model probabilistic causality. Transformers are sometimes considered a fully connected graph neural network, which can be used for modeling causal graphs. One additional supporting evidence on the finite step reasoning hypothesis is that "train of thought" improves the performance of LLMs[1], meaning that letting the model explain itself explicitly reduces the amount of implicit "reasoning" steps that need to happen within the model. Additionally, while we don't…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by xianshou

Mon, 03 Apr 2023 15:19:28 GMT

Decent read: this. Better read: the original paper demonstrating that prompting chain-of-thought reasoning elicits superior results. TLDR, give examples of working out the problem step-by-step, encourage GPT to emulate, and it's capable of solving challenges it would completely miss otherwise. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by vsareto

Wed, 29 Mar 2023 15:24:18 GMT

Like the sister WaPo article hyping up this job title, also involving Anthropic (https://archive.is/pvwlx), this is still a super small market and only red-hot only because of Anthropic's job posting. It's like watching a penny stock have a huge price spike when there's one buyer and one seller. In addition, I can't fathom paying $300k for skills less than a Ph.D or self-directed research. You'll be wanting to find emergent stuff like this and not just crafting prompts to get the right response: https://arxiv.org/abs/2201.11903 This is probably what prompt engineering should be about, not…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by Dzugaru

Sat, 25 Mar 2023 10:00:29 GMT

> but could be fixed How? The problem is known for a while, for example this article [0] mentions it (as Chain of Thought reasoning). You could think that just having a scratchpad of tokens is enough - you can arguably plan, backtrack and rewrite there [1], right? But this doesn't really work, at least yet - maybe because it wasn't trained for that - and maybe ChatGPT massive logs (probably available only for OpenAI) can help. But the Microsoft report [2] suggests we need a different architerture and/or algorithms? They mention lack of planning and retrospective thinking as a huge problem for…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by nl

Mon, 20 Mar 2023 05:27:25 GMT

> the first CoT paper introduced few shot examples It doesn't actually. See https://arxiv.org/pdf/2201.11903.pdf Perhaps you are thinking of the GPT-3 paper ("Language Models are Few-Shot Learners") which has plenty of these examples.

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by soraki_soladead

Sun, 19 Mar 2023 20:27:45 GMT

Sure. A few below but far from exhaustive: - https://arxiv.org/abs/1909.07528 - https://arxiv.org/abs/2212.10403 - https://arxiv.org/abs/2201.11903 - https://arxiv.org/abs/2210.13382 There are also literally hundreds of articles and tweet threads about it. Moreover, as I said, you can test many of my claims above directly using readily available LLMs. GP has a much harder defense. They have to prove that despite all of these capabilities that LLMs are not intelligent. That the mechanisms by which humans possess intelligence is fundamentally distinct from a computer’s ability to exhibit the…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by williamcotton

Thu, 02 Mar 2023 20:46:25 GMT

Here you go, here's a bunch of papers that you have not read. If you had read them then you would know that the errors are predictable and therefore there are many measurable ways to make improvements. Toolformer: Language Models Can Teach Themselves to Use Tools: https://arxiv.org/abs/2302.04761 PAL: Program-aided Language Models: https://arxiv.org/abs/2211.10435 TALM: Tool Augmented Language Models: https://arxiv.org/abs/2205.12255 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models: https://arxiv.org/abs/2201.11903 Survey of Hallucination in Natural Language Generation…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by visarga

Tue, 28 Feb 2023 05:22:51 GMT

Chain-of-thought is not the same with direct prompting. Step by step is better. > Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by danielbln

Tue, 21 Feb 2023 08:44:19 GMT

They literally "do context", as they do in-context learning. Also, factuality can effectively be solved by chain-of-thought prompting[0] and the use of external tools[1], also see toolformerzero[2] for a simple example. [0]: https://arxiv.org/abs/2201.11903 [1]: https://arxiv.org/abs/2302.04761 [2]: https://toolformerzero.com/ [2]: https://toolformerzero.com/

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by LesZedCB

Tue, 14 Feb 2023 07:29:14 GMT

it really does tho https://arxiv.org/abs/2201.11903 just in a limited capacity

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by eternalban

Sun, 15 Jan 2023 03:44:34 GMT

Using chain of thought [slightly modified] example from https://arxiv.org/abs/2201.11903 (ref'd in OP) Prompt: Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now? A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11. Q: The room has 19 chairs. We are using 10 and then bought 9 more, how many chairs do we have in the room? response A: The room started with 19 chairs. We are using 10 of them, so we have 19 - 10 = 9 chairs left in the room. We then bought 9…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by tuxracer

Sat, 24 Dec 2022 10:49:51 GMT

If you ask it to write out the steps ahead of time you'll often get a more accurate answer [1] Q: "How far is Boston from Boston? Write down your steps before you answer." A: "Boston is a city located in the state of Massachusetts in the United States. To determine the distance from Boston to Boston, we can follow these steps: 1. Determine the coordinates of the starting location, which is Boston, Massachusetts. We can use a map or a GPS tool to find the latitude and longitude of Boston. 2. Determine the coordinates of the destination, which is also Boston, Massachusetts. Again, we can use a…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — HN submission

Mon, 19 Dec 2022 15:29:09 GMT

Chain of Thought Prompting Elicits Reasoning in Large Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by _0ffh

Sat, 15 Oct 2022 11:59:09 GMT

Btw, here's an example of how even a very simple zero-shot/prompt-engineering attempt to introduce a bit of system 2 reasoning into a language model can improve results. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by yababa_y

Sat, 23 Jul 2022 19:39:03 GMT

Yes, you are doing it wrong, but also this is a hard challenge. Here is some advice from a recent thread (https://twitter.com/goodside/status/1547613735543402500): > Note the useful deception at the end of this prompt: We tell the model what follows are correct training examples, but we silently end this list after k examples and begin generating completions. Adding “Now you try:” or similar makes it more prone to fail. > Never actually ask GPT-3 to try do something. It’s like with Yoda — If it thinks it’s trying, it’s likely to fail. Instead, announce you have correct examples for it, give…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by cmorez

Sat, 23 Jul 2022 13:28:33 GMT

This has the same flavor as the initial criticisms of AlphaGo. "It will never be able to play anything other than Go", cue AlphaZero. "It will never be able to do so without being told the rules", cue MuZero. "It will never be able to do so without obscene amounts of data", cue EfficientZero. --- It has to be spoonfed because 1) It literally cannot see individual digits. (BPEs) 2) It has to infer context (mystery novel, comment section, textbook) 3) It has a fixed compute-budget per output. (96 layers per token, from quantum physics to translation). To make Language Models useful one must…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by skybrian

Mon, 16 May 2022 22:57:06 GMT

You're right for GPT 3, but it's an example of chain of thought reasoning, which seems to be a new area of research [1] and might get integrated into newer versions: [1] https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by DavidSJ

Fri, 13 May 2022 06:00:58 GMT

System 2 could be close behind System 2 by building on System 1 but it isn't clear how long that will take. This is happening since a few months ago: Wei et al (2022). Chain of Thought Prompting Elicits Reasoning in Large Language Models. https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by visarga

Mon, 02 May 2022 18:58:37 GMT

It's a model mismatch, not an inherent impossibility. A calculator needs to have an adaptive number of intermediate steps. Usually our models have fixed depth, but in auto-regressive modelling the tape can become longer as needed by the stepwise algorithm. Recent models show LMs can do arithmetic, symbolic math and common sense chain-of-thought step by step reasoning and reach much higher accuracies. In other words, we too can't do three digit multiplication in our heads reliably, but can do it much better on paper, step by step. The problem you were mentioning is caused by the bad approach…

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by DavidSJ

Sun, 01 May 2022 01:48:19 GMT

A lot of people can't subitize past four. Counting is another matter: it's a symbolic, deliberate, step-by-step activity. Arguably most neural networks don't do symbolic, step-by-step reasoning "natively", and maybe human beings don't either. But they can be told to, and then the same network becomes much smarter: https://arxiv.org/abs/2201.11903

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

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — HN submission

Mon, 11 Apr 2022 14:08:01 GMT

Chain of Thought Prompting Elicits Reasoning in Large Language Models

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — mentioned by visarga

Mon, 04 Apr 2022 19:50:48 GMT

Interesting that they used Chain of Thought Prompting[1] for improved reasoning so soon after its publication. Also related to DeepMind AlphaCode which generates code and filters results by unit tests, while Chain of Thought Prompting filters by checking for correct answer at the end. Seems like language models can generate more training data for language models in an iterative manner. [1] https://arxiv.org/abs/2201.11903

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