Fgveribench Eval

---
name: fgveribench-eval
description: Evaluates an LLM verifier's ability to rank multiple candidate answers by their factual correctness and error severity across single-hop and multi-hop questions, using external knowledge retrieval and fine-grained scoring. Use when the user wants to benchmark on FGVeriBench, or asks about evaluating this task. Reports Kendall-tau.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2601.03605
  bibtex_key: huang2026diva
  confidence: high
---

# fgveribench-eval

> DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier — Hui Huang, Muyun Yang, Yuki Arase (2026) (arXiv:2601.03605, 2026)

## What this evaluates

Evaluates an LLM verifier's ability to rank multiple candidate answers by their factual correctness and error severity across single-hop and multi-hop questions, using external knowledge retrieval and fine-grained scoring.

## Datasets

- **FGVeriBench** — total ?; splits: test (-1); repo https://github.com/HuihuiChyan/FactVeri-SFT

## Metrics

- `Kendall-tau` **(primary)** — range: [-1, 1]
  - Kendall rank correlation coefficient measuring the ordinal association between predicted factuality scores and ground-truth scores. Ranges from -1 to 1, with 1 indicating perfect agreement.
- `P@1` — range: [0, 1]
  - Precision at rank 1; measures whether the verifier correctly identifies the most factual answer as the top-ranked candidate.

## Input / output format

**Input**: A question, a set of candidate answers, and retrieved external evidence (from WebSearch and/or LocalSearch).

**Output**: A fine-grained factuality score for each candidate answer, or a binary correct/incorrect label for binary verification settings.

## Scoring recipe

```python
def compute_ktau(pred_scores, gold_scores):
    return kendalltau(pred_scores, gold_scores).correlation

def compute_p1(pred_scores, gold_scores):
    return 1.0 if np.argmax(pred_scores) == np.argmax(gold_scores) else 0.0
```

## Common pitfalls

- Relying solely on the LLM's internal parametric knowledge without external retrieval causes significant performance drops, as static weights cannot update over time.
- Fine-grained verification requires ranking candidates by error severity rather than simple binary correctness; models optimized only for binary accuracy often fail to capture nuanced factuality differences.

## Evidence (verbatim from paper)

> Table 7: Kendall-tau correlation coefficient of different knowledge sources on FGVeriBench.

## Citation

```bibtex
@misc{huang2026diva,
  title={DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier},
  author={Hui Huang, Muyun Yang, Yuki Arase (2026)},
  year={2026},
  note={arXiv:2601.03605}
}
```

- arXiv: 2601.03605