EvasionBench

{
    "uid": "4addbff893b81f64131fdc712d7a6d9a",
    "question": "What is the expected margin for Q4?",
    "answer": "We expect it to be 32%.",
    "eva4b_label": "direct"
}

from datasets import load_dataset

dataset = load_dataset("FutureMa/EvasionBench")

import pandas as pd

df = pd.read_parquet("evasionbench_17k_eva4b_labels_dedup.parquet")

from datasets import load_dataset
from transformers import pipeline

# Load dataset
dataset = load_dataset("FutureMa/EvasionBench")

# Load model using text-generation pipeline
pipe = pipeline("text-generation", model="FutureMa/Eva-4B-V2", device_map="auto")

# Get a sample
sample = dataset["train"][0]
question = sample["question"]
answer = sample["answer"]

# Prepare prompt
prompt = f"""You are a financial analyst. Your task is to Detect Evasive Answers in Financial Q&A

Question: {question}
Answer: {answer}

Response format:
```json
{{"label": "direct|intermediate|fully_evasive"}}
```

Answer in ```json content, no other text"""

# Run inference
result = pipe(prompt, max_new_tokens=64, do_sample=False)
print(result[0]["generated_text"])

@misc{ma2026evasionbenchlargescalebenchmarkdetecting,
  title={EvasionBench: A Large-Scale Benchmark for Detecting Managerial Evasion in Earnings Call Q&A},
  author={Shijian Ma and Yan Lin and Yi Yang},
  year={2026},
  eprint={2601.09142},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2601.09142}
}