Assistant Professor at UMBC working on story generation, #AAC, and an #AI #DnD dungeon master.
♿💗💜💙♾️
Here's more hashtags:
#NLP #NLProc #NLG #CogSci #speech #ComputationalCreativity
| Website | https://laramartin.net |
| Pronouns | she/they |
Next, in Findings of ACL, there's "CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding" by Yijiang River Dong, myself, & @ccb
I've mentioned this work before, but now it's published! Here, we used code-based #LLMs like Codex (RIP) to provide structure in story understanding, which we saw helps the LLM figure out what characters are doing better!
https://arxiv.org/abs/2212.10754
2/2 #ACL2023
Story generation and understanding -- as with all NLG/NLU tasks -- has seen a surge in neurosymbolic work. Researchers have recognized that, while large language models (LLMs) have tremendous utility, they can be augmented with symbolic means to be even better and to make up for any flaws that the neural networks might have. However, symbolic methods are extremely costly in terms of the amount of time and expertise needed to create them. In this work, we capitalize on state-of-the-art Code-LLMs, such as Codex, to bootstrap the use of symbolic methods for tracking the state of stories and aiding in story understanding. We show that our CoRRPUS system and abstracted prompting procedures can beat current state-of-the-art structured LLM techniques on pre-existing story understanding tasks (bAbI Task 2 and Re^3) with minimal hand engineering. We hope that this work can help highlight the importance of symbolic representations and specialized prompting for LLMs as these models require some guidance for performing reasoning tasks properly.
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.
My wife (gorgeous roboticist Cassie Kent) and I dressed up as #Catra and #Adora this
#halloween. 😻