More tips:
* Don't plan things too tightly, let the story flow from the actions of the players. Yes, this is generic advice for #TTRPG generally, but it's even more important in #PBP games.
* Put some effort into battlemaps. PBP can be challenging from an immersion perspective, but good maps can make a big difference in how battles or even exploration work out. If on #Discord using #Avrae, learn to love otfbm.io -- even with its quirks. (2/2)
How I use Avrae
Avrae is a very capable D&D discord bot made by DnDBeyond. It's complicated. In the spirit of 'complex tools, used simply' I want to share how I use it when I'm GMing a game. I have a go-to set of 10 or so commands that I can remember and that I use. I've tried to use more of it in the past but my brain has been full for a long time and I can't pick up these tools like I used to.
Yay! 2/2 papers accepted at #ACL2023 !
First, in the main conference, there's
"FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information" by @zhuexe, Karmanya Aggarwal, Alex Feng, myself, & @ccb
Contributions:
- A corpus of data from people playing #DnD on Discord using a bot called #Avrae, made by @zhuexe himself. Avrae tracks vital game state information for D&D.
- #LLMs "translating" Avrae commands into plain English.
https://arxiv.org/abs/2305.01528
1/2
Dungeons & Dragons (D&D) is a tabletop roleplaying game with complex natural language interactions between players and hidden state information. Recent work has shown that large language models (LLMs) that have access to state information can generate higher quality game turns than LLMs that use dialog history alone. However, previous work used game state information that was heuristically created and was not a true gold standard game state. We present FIREBALL, a large dataset containing nearly 25,000 unique sessions from real D&D gameplay on Discord with true game state info. We recorded game play sessions of players who used the Avrae bot, which was developed to aid people in playing D&D online, capturing language, game commands and underlying game state information. We demonstrate that FIREBALL can improve natural language generation (NLG) by using Avrae state information, improving both automated metrics and human judgments of quality. Additionally, we show that LLMs can generate executable Avrae commands, particularly after finetuning.
Snarky (he/him/his)
whitebeard
Lara J. Martin
Lyndon Hood