Toolformer: Language Models Can Teach Themselves to Use Tools · HackerPapers discussions

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by seanhunter

Thu, 23 Nov 2023 09:48:07 GMT

It does. This is the plugins methodology described in the toolformers paper which I've linked elsewhere[1]. The model learns that for certain types of problems certain specific "tools" are the best way to solve the problem. The problem is of course it's simple to argue that the LLM learns to use the tool(s) and can't reason itself about the underlying problem. The question boils down to whether you're more interested in machines which can think (whatever that means) or having a super-powered co-pilot which can help with a wide variety of tasks. I'm quite biased towards the second so I have…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by seanhunter

Thu, 23 Nov 2023 08:45:40 GMT

Nothing, and there are methods which allow these types of models to learn to use special purpose tools of this kind[1]. [1] https://arxiv.org/abs/2302.04761 Toolformer: Language Models Can Teach Themselves to Use Tools

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by manvel_hn

Mon, 24 Jul 2023 13:45:44 GMT

Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761 Older one, but still very nice work.

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by seanhunter

Wed, 24 May 2023 10:44:45 GMT

That’s sort of what happens in the “toolformer” paper[1] which sets out the basic architecture by which things like chatGPT plugins work. Language models can learn to use “tools” provided by plugins. Those tools might themselves bee the specialized models you are describing (although for some plugins they could be a non-AI tool such as web search or whatever). [1] https://arxiv.org/pdf/2302.04761.pdf

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by kz919

Sat, 20 May 2023 02:17:32 GMT

you just need to teach it to use a calculator https://arxiv.org/pdf/2302.04761.pdf

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by famouswaffles

Sat, 13 May 2023 02:37:54 GMT

It should be in line with the likes of this - https://arxiv.org/abs/2302.04761 or https://twitter.com/minosvasilias/status/1627076214639976449 I didn't say guardrail to mean anything particularly elaborate. The pre-prompt for Bing has instructions to avoid adversarial arguments.

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by johntb86

Thu, 27 Apr 2023 23:00:57 GMT

This document seems to have been written before the toolformer paper[0], which fine tunes the model to use tools (e.g search) to retrieve information. [0]: https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by Version467

Mon, 03 Apr 2023 08:02:00 GMT

The recent post from Stephen Wolfram[1] is pretty good as an introduction, but I haven't seen any super comprehensive material that tries do dissect all the interesting behaviour we see in the really big llms. For that just reading the relevant papers themselves has been pretty fruitful for me. Some of them are actually very well written, even if you aren't used to reading scientific papers. I can recommend the Sparks of AGI paper[2] and the toolformer paper[3]. Obviously there's much more out there, those three things are a pretty good read. [1]…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by ninjin

Tue, 28 Mar 2023 09:27:45 GMT

I am actually not quite sure what would be best to recommend, as the pandemic has seen me lag behind the zeitgeist somewhat. A recent favourite would be the Toolformer paper [1], that I intend to read in detail later today. If an LLM would be able to use external tools efficiently, it could be rather powerful and perhaps allow us to scale down the parameter sizes, which somewhat fascinates me. [1]: https://arxiv.org/abs/2302.04761 Other research questions, but without concrete papers to reference to that current keeps me up at night: 1.) to which degree can we train substantially smaller LLMs…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by pornel

Tue, 28 Mar 2023 04:12:14 GMT

> LLMs can't to my knowledge process a request into a lookup on say an actual database of facts at the moment or parse a request into API actions. They can: https://arxiv.org/abs/2302.04761 > In this paper, we show that LMs can teach themselves to use external tools

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by jeadie

Sun, 26 Mar 2023 22:33:43 GMT

I think I've read it's based off Toolformer (https://arxiv.org/pdf/2302.04761.pdf)

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by grafs50

Sun, 19 Mar 2023 05:55:35 GMT

They already can: https://arxiv.org/abs/2302.04761 (Toolformer) There's even a zero-shot version based on prompt engineering: https://toolformerzero.com/.

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by wcoenen

Fri, 17 Mar 2023 20:54:38 GMT

Bing chat already hooks into a web search tool. It shows "Searching for: ..." when it does that. This is kind of the point of Bing chat. edit: a paper about how to hook up LLMs to any external tool https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by goldwelder42

Fri, 17 Mar 2023 18:29:02 GMT

Since the GPT-4 paper didn't reveal any details of their model, it's possible that GPT-4 is already using some variant of toolformer (https://arxiv.org/abs/2302.04761).

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by sprobertson

Tue, 14 Mar 2023 21:47:54 GMT

He likely meant techniques such as ToolFormer[1] where the language model will output a "request" (in some text syntax) that another system can parse, run and report back. [1] https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by jkbyc

Thu, 09 Mar 2023 12:46:24 GMT

That's called Toolformer (Facebook AI Research): https://arxiv.org/abs/2302.04761 Toolformer: Language Models Can Teach Themselves to Use Tools

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

Toolformer: Language Models Can Teach Themselves to Use Tools — 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.

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by jackblemming

Wed, 01 Mar 2023 03:07:49 GMT

Hooking ChatGPT (and similar architectures) into applications is going to be the next big thing. It just takes time to hook up various systems. Eventually a vision module will be integrated and it will probably be able to "figure out" most systems. There's a lot of money to be made in hooking up these "brains" into apps. I hope people get on it, since it will be quite convenient. See: Act-1: https://news.ycombinator.com/item?id=32842860 Open-Assistant: https://github.com/LAION-AI/Open-Assistant Toolformer: https://arxiv.org/abs/2302.04761 Understanding HTML with LLMs…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by williamcotton

Tue, 28 Feb 2023 16:18:26 GMT

Here’s some recent ML work from Meta that I really like: Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by imranq

Fri, 24 Feb 2023 22:37:58 GMT

You can make small LLMs more performant than large ones like GPT-3 by fine-tuning on specific tasks or providing them tools to offload precise calculations: e.g. Toolformer: https://arxiv.org/abs/2302.04761 which uses APIs and functions to improve GPT-J beyond GPT-3 for various tasks

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by BoorishBears

Thu, 23 Feb 2023 22:58:59 GMT

There's research being done on this: https://arxiv.org/abs/2302.04761 At its core using an LM alone to solve factual problems seems silly: It's not unlike asking Dall-E to draw DOT compliant road signs. I've gone at length at how unfortunate it would be if LMs start to get a bad rap because they're being shoehorned into being "Ask Jeeves 2.0" when they could be so much more.

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by williamcotton

Thu, 23 Feb 2023 15:09:38 GMT

Fine-tuning on smaller models like GPT-J (also trained on The Pile) worked well for Toolformer: https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by williamcotton

Tue, 21 Feb 2023 19:51:49 GMT

Using the terminology that I'm working with this is an example of a second-order analytic augmentation! Here's another approach of second-order analytic augmentation, PAL: https://reasonwithpal.com Third-order, Toolformer: https://arxiv.org/abs/2302.04761 Third-order, Bing: https://www.williamcotton.com/articles/bing-third-order Third-order, LangChain Agents: https://langchain.readthedocs.io/en/latest/modules/agents/ge... The difference isn't in what is going on but rather with framing the approach within the analytic-synthetic distinction developed by Kant and the analytic philosophers who…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by williamcotton

Tue, 21 Feb 2023 17:52:58 GMT

One recent paper to be added to this list of Approaches/Techniques is: Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761 The authors show a valuable method of using prompts to generate training data to be used for fine-tuning. Check out Appendix A.2 in the paper for the example prompts.

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

Toolformer: Language Models Can Teach Themselves to Use Tools — 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.

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by valine

Sat, 18 Feb 2023 18:59:27 GMT

In their current iteration the models are very neutered. It’s been demonstrated that GPT models are fairly good at choosing when to perform a task. Obviously lots of APIs and machinery is needed to actually perform tasks, but the heavy lifting “intelligence” portion can be almost entirely performed by our existing models. Some basic text based APIs that would quickly improve LLM utility: Calculators Database storage and retrieval Web access (already kind of done by bing) Shell scripting Thinking further into the future of multimodal models, it’s not hard to imagine this sort of thing could be…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by valine

Mon, 13 Feb 2023 18:02:59 GMT

Except it’s already been shown LLMs can do exactly that. You can prime the model to insert something like ${API CALL HERE} into its output. Then it’s just a matter of finding that string and calling the api. Toolformer does something really neat where they make the API call during training and compare next word probability of the API result with the generated result. This allows the model learn when to make API calls in a self supervised way. https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by btown

Mon, 13 Feb 2023 17:57:37 GMT

I love the mental model of GPT as only one part of the brain, but I believe that the integration of other "parts" of the brain will come sooner than you think. See, for instance, https://twitter.com/mathemagic1an/status/1624870248221663232 / https://arxiv.org/abs/2302.04761 where the language model is used to create training data that allows it to emit tokens that function as lookup oracles by interacting with external APIs. And an LLM can itself understand when a document is internally inconsistent, relative to other documents, so it can integrate the results of these oracles if properly…

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

Toolformer: Language Models Can Teach Themselves to Use Tools — HN submission

Sat, 11 Feb 2023 22:52:17 GMT

Toolformer: Language Models Can Teach Themselves to Use Tools

220 points; 45 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Toolformer: Language Models Can Teach Themselves to Use Tools — HN submission

Sat, 11 Feb 2023 09:30:33 GMT

Toolformer: Language Models Can Teach Themselves to Use Tools

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

Toolformer: Language Models Can Teach Themselves to Use Tools — mentioned by localhost

Fri, 10 Feb 2023 03:23:58 GMT

Relevant to this discussion is the Toolformer paper that was just released today from Meta AI. To me the exciting result from the paper is that it appears that much smaller models can be used to translate human intent into actions: https://arxiv.org/abs/2302.04761

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

Toolformer: Language Models Can Teach Themselves to Use Tools — HN submission

Fri, 10 Feb 2023 01:59:11 GMT

Toolformer: Language models can teach themselves to use tools

155 points; 18 discussion replies on HN. Paper and source history. A submission is not an endorsement.