AVCORP Detector: Qwen3-8B LoRA Adapters

LoRA adapters for the deception detector in AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind. Each adapter finetunes Qwen3-8B on AVCORP to act as the Investigator in Avalon: it reads the game history and discussion of a round, writes a Theory of Mind reasoning trace, and names the players it believes are Evil.

Paper: https://arxiv.org/abs/2611.10176
Code, corpus, and prompts: https://github.com/fardinsaad/_AVCORP_ (see Detector/)
Dataset: https://huggingface.co/datasets/fardinsaad/AVCORP
Training: SFT, then GRPO (TRL), on one NVIDIA H100
LoRA: rank 32, alpha 64, dropout 0.05, all linear layers (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)

Adapters

Each configuration folder holds two adapters: sft/ (after SFT) and grpo/ (after SFT, then GRPO). Run numbers match Detector/ in the GitHub repository.

Folder	Run	Output variant	Rewards
`tactic-revised/` (best)	7	trace + tactic labels	revised
`tactic-original/`	6	trace + tactic labels	original
`trace-revised/seed{1,2,3}/`	5	trace labels	revised
`trace-original/seed{1,2,3}/`	4	trace labels	original

Results

Exact match: the share of the 25 held-out AVCORP games in which the game-ending deduction names both Evil players. In evaluation, each round's prompt contains the detector's own earlier traces.

Configuration	Untrained	SFT	SFT + GRPO
Run 7: `tactic-revised`	48%	48%	72%
Run 6: `tactic-original`	48%	52%	48%
Run 5: `trace-revised` (mean of 3 seeds)	24%	38.7%	64.0%
Run 4: `trace-original` (mean of 3 seeds)	24%	36.0%	33.3%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base, "fardinsaad/AVCORP-detector", subfolder="tactic-revised/grpo")

Each adapter loads on its own on top of the base model. The prompt format and the evaluation script are in Detector/ of the GitHub repository.

Citation

@article{Saad+26:AVCORP,
  author  = {Fardin Saad and Zhe Zhang and Sanjana Cheerla and Amanul Haque and Munindar P. Singh},
  title   = {{AVCORP}: {I}dentifying and Resisting Deception via {C}ommunication {T}heory and {T}heory of {M}ind},
  journal = {CoRR},
  volume  = {abs/2611.10176},
  month   = nov,
  year    = 2026,
  url     = {https://arxiv.org/abs/2611.10176}
}