PAL: Program-aided Language Models · HackerPapers discussions

PAL: Program-aided Language Models — mentioned by axiom92

Sun, 30 Nov 2025 20:25:49 GMT

And even before this work, there was "PAL: Program-aided Language Models" (https://arxiv.org/abs/2211.10435, https://reasonwithpal.com/). Afaik PaLM (Google's OG big models) tried this trick, but it didn't work for them. I think it's because PaL used descriptive inline comments + meaningful variable names. Compare the following: ```python # calculate the remaining apples apples_left = apples_bought - apples_eaten ``` vs. ```python x = y - z ``` We have ablations in https://arxiv.org/abs/2211.10435 showing that both are indeed useful (see "Crafting prompts for PAL").

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

PAL: Program-aided Language Models — HN submission

Wed, 05 Apr 2023 21:21:00 GMT

Show HN: Guesstimate – Generate a spreadsheet-like interface for any question

Hey HN, I built something to estimate things: https://guesstimate.ai Unlike ChatGPT, Guesstimate can do calculations. I asked both to calculate the time it'd take an object to fall from the ISS to sea level (about 400km, assume no air resistance). ChatGPT, using a lot of words, did everything correctly right until the last step [1]. Guesstimate took a similar approach, but it got the right answer: https://guesstimate.ai/e/est114xrhnj1f6h9cm44 I think it's absurd that we're trying to teach LLMs basic arithmetic when there's a literal arithmetic processing unit right next to the GPU. You…

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

PAL: Program-aided 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.

PAL: Program-aided Language Models — HN submission

Tue, 31 Jan 2023 02:51:56 GMT

Program Aided Language Models

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

PAL: Program-aided Language Models — mentioned by gandalfgeek

Sat, 21 Jan 2023 03:22:37 GMT

I was surprised to see the omission of a prompt technique called program-aided prompting. Paper: https://arxiv.org/abs/2211.10435 GitHub: https://github.com/reasoning-machines/pal tl;dr -- LLMs are bad at basic arithmetic and logic (as their opening examples with math word problems show), but they do much better if instead of asking them for the answer, you ask for code to compute the answer. Then evaluate or run the code to get the answer.

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