paper-with-me

홈 › Papers

A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis

2025-02-13 · Kentaro Imajo, Masanori Hirano, Shuji Suzuki, Hiroaki Mikami

Evaluating the open-ended text generation of large language models (LLMs) is challenging because of the lack of a clear ground truth and the high cost of human or LLM-based assessments. We propose a novel benchmark that evaluates LLMs using n-gram statistics and rules, without relying on human judgement or LLM-as-a-judge approaches. Using 50 question and reference answer sets, we introduce three new metrics based on n-grams and rules: Fluency, Truthfulness, and Helpfulness. Our benchmark strongly correlates with GPT-4o-based evaluations while requiring significantly fewer computational resources, demonstrating its effectiveness as a scalable alternative for assessing LLMs' open-ended generation capabilities.

📄 PDF Abstract BibTeX arXiv:2502.09316

Code (1)

pfnet-research/pfgen-bench 공식 구현

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Free-Text Evaluation of LLMs for 5G Domain Knowledge and Fault Analysis using LLM-as-Judge

2026-08-21 · Rishiraj Sengupta, Sotiris Chatzimiltis, Mohammad Shojafar, Xiatian Zhu arxiv

Real-world fault analysis in 5G and emerging 6G networks demands domain expertise to analyze free-text diagnostics, including root-cause explanations and recommended actions. LLMs have emerged as a promising approach to …

Fault DiagnosisText Generation

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

2026-05-29 · Wai-Chung Kwan, Aryo Pradipta Gema, Joshua Ong Jun Leang, Pasquale Minervini arxiv

Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or frontier-model judges. We introduce SCO…

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation

2024-11-27 · CVPR 2025 1 · Pengfei Zhou, Xiaopeng Peng, Jiajun Song, Chuanhao Li 외

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multi…

Image Generationmultimodal generationText Generation

Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling

2026-07-02 · Dazhi Fu, Jiuding Yang, Yiwen Guo, Jicong Fan arxiv

Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluatio…

Reinforcement Learning

CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

2026-03-02 · Ziyi Zhu, Olivier Tieleman, Alexey Bukhtiyarov, Jinghong Chen arxiv

LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be averaged out by increasing the number of scenarios or generations. These bias…