From time to time, I see a tool to present a discussion as a tree with arguments for and against it.<p>Unless it is a school essay, arguments don't go that way.<p>It is usually harder to encompass what a node (an atomic fact) is and what a link is (it usually goes beyond "support" and "counter"). Very often, this structure is not a tree. Maybe a DAG with weighted edges, but if it were that straightforward - knowledge graphs would simply work.<p>Instead of rehashing the same tree approach, we should adopt something closer to an LLM-embedding approach - for a given statement, we should have "relevant statements" with an additional dimension if it supports, counters, expands, provides an example, and so on. In this case, it wouldn't even be a DAG.
For an example of how these may be used, Kialo [1] uses a form of argument maps for structured debate. There's also an Obsidian plugin for argument maps [2], tho it's a bit out of date.<p>[1]: <a href="https://www.kialo.com" rel="nofollow">https://www.kialo.com</a><p>[2]: <a href="https://github.com/amdecker/obsidian-argdown-plugin">https://github.com/amdecker/obsidian-argdown-plugin</a>
It was useful during WebGPU development [1] given that some topics were very nuanced in debate.<p>[1] <a href="https://github.com/kvark/webgpu-debate">https://github.com/kvark/webgpu-debate</a>
I am the author of some recent literature on Competitive Debate datasets for the NLP community:<p>1. <a href="https://aclanthology.org/2020.argmining-1.1/" rel="nofollow">https://aclanthology.org/2020.argmining-1.1/</a><p>2. <a href="https://paperswithcode.com/paper/opendebateevidence-a-massive-scale-argument" rel="nofollow">https://paperswithcode.com/paper/opendebateevidence-a-massiv...</a> (under review at a main conference, but we had an acceptance to ARGMIN 2024 at ACL 2024 which we declined)<p>I'm very interested in talking with the authors of this work about how we can think about structured argumentation notations like this for the American Competitive debate community. American Competitive Debaters have their own informal markdown-like structures and fuzzy-syntax of their formatting alongside so much jargon that I really want to see how it can map to something like Argdown.
Is there some reason this is all focused around yes/no questions or a single statement? Is it like a standard format that all topics can be reworded to?<p>I'm wondering if this could this be used for something like comparing alternatives to solve a problem. In that case I'd expect the root to be a description of the problem, then alternatives, then pros-cons for those alternatives.<p>I'd never heard of this at all before despite searching, so I imagine there's a lot I don't know.
I tried writing diary entries in argdown for a while.
It was fun having this big visual map of all my thoughts on everything, especially when I reused premises a lot. It wasn't particularly useful though.
Wow, it’s crazy seeing your dreams randomly pop up on hacker news. Guess I’ll be switching to this syntax!<p>OP, if you’re the author: any plans for next steps? I’ll be folding this into my upcoming book and website (and almost certainly extending it a bit), so I’d be curious to hear if there’s other large scale projects underway.<p>Beautiful docs btw, this style should be a lesson for all of us. I guess you’d expect someone interested in arguments to write clearly lol
I might know nothing about debates, but in my impression you always make the diagram that does its job best. Argdown seems to constrain everything to its framework and forces the style of the output.<p>Also, Mermaid (<a href="https://mermaid.js.org/" rel="nofollow">https://mermaid.js.org/</a>) exists.
These argdown ligatures are nifty. I also really like Unicode logic symbols because they make annotation and expressions readable.<p><a href="https://en.wikipedia.org/wiki/List_of_logic_symbols" rel="nofollow">https://en.wikipedia.org/wiki/List_of_logic_symbols</a><p>These can be especially helpful for Causal Analysis based on System Theory (CAST) which is similar to root cause analysis plus uses more logical dependencies.
There was a website called (I believe) Arguman (way) in the past, that used this kind of thing. It allowed everyone to add arguments, rebuttals, such a thing, and up/downvote them. Last time I looked at it, it was down (still on wayback, but it was a webapp, so it never really loads anything).<p>Edit: it's... "up", but suddenly Turkish and broken: <a href="https://arguman.org" rel="nofollow">https://arguman.org</a>
Mapping different viewpoints to combat disinformation or create better policies is key in this age. I'd wish to see a better integration with cognitive psychology and it's overview of biases, also in relation to personal insecurities, trauma and with agogy and education, like The Evidence Toolkit.<p>A short overview of the Argumentation theory and tooling field:<p>“Within computer science, the ArgMAS workshop series (Argumentation in Multi-Agent Systems), the CMNA workshop series,[34] and the COMMA Conference, are regular annual events attracting participants from every continent. The journal Argument & Computation is dedicated to exploring the intersection between argumentation and computer science. ArgMining is a workshop series dedicated specifically to the related argument mining task.
Data from the collaborative structured online argumentation platform Kialo has been used to train and to evaluate natural language processing AI systems such as, most commonly, BERT and its variants.”
<a href="https://en.m.wikipedia.org/wiki/Argumentation_theory" rel="nofollow">https://en.m.wikipedia.org/wiki/Argumentation_theory</a><p><a href="https://en.m.wikipedia.org/wiki/Argument_technology" rel="nofollow">https://en.m.wikipedia.org/wiki/Argument_technology</a><p><a href="https://en.m.wikipedia.org/wiki/Argumentation_framework" rel="nofollow">https://en.m.wikipedia.org/wiki/Argumentation_framework</a><p>Sibling tooling (with help from Sonnet and Wikipedia):<p>1. Argument Interchange Format (AIF):
This is a standardized format for representing argumentative structures in a machine-readable way. It's used in various academic tools and research projects. 2006<p>2. Rationale:
A software tool developed for academic use, particularly in teaching critical thinking and argument analysis. It offers more structured mapping capabilities than Kialo. 2004<p>3. Araucaria:
An open-source argument mapping software developed by researchers at the University of Dundee. It's designed for analyzing and diagramming arguments. 2001<p>4. ArgDown:
A markdown-like language for creating argument maps, which can be useful for programmatic approaches to argument analysis. 2016<p>5. OVA (Online Visualization of Argument):
A web-based tool for argument analysis and visualization, developed by researchers at the University of Dundee. 2010<p>6. Argunet:
An open-source argument mapping software that allows for collaborative work and integrates with a database of arguments. 2007<p>7. AGORA-net:
A web-based platform for argument reconstruction and evaluation, used in academic settings. 2013<p>8. Kialo 2017
<a href="https://en.m.wikipedia.org/wiki/Kialo" rel="nofollow">https://en.m.wikipedia.org/wiki/Kialo</a><p>9. ADA tools. Gregor Betz (2022). "Natural-Language Multi-Agent Simulations of Argumentative Opinion Dynamics". Journal of Artificial Societies and Social Simulation. 25: 2. arXiv:2104.06737. doi:10.18564/jasss.4725. S2CID 233231231
<a href="https://www.gregorbetz.de/" rel="nofollow">https://www.gregorbetz.de/</a><p>10. Argument Analytics
<a href="http://analytics.arg.tech/" rel="nofollow">http://analytics.arg.tech/</a><p>11. IBM's Grand Challenge, Project Debater 2011- Published in Nature in March 2021
<a href="https://en.m.wikipedia.org/wiki/Project_Debater" rel="nofollow">https://en.m.wikipedia.org/wiki/Project_Debater</a><p>12. German research funder, DFG's nationwide research programme on Robust Argumentation Machines, RATIO. 2019 <a href="https://spp-ratio.de/" rel="nofollow">https://spp-ratio.de/</a><p>13. UK nationwide deployment of The Evidence Toolkit by the BBC. 2019
<a href="https://www.bbc.co.uk/teach/young-reporter/articles/z6v3hcw" rel="nofollow">https://www.bbc.co.uk/teach/young-reporter/articles/z6v3hcw</a>