Imagen de Portada

Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ruan, Jie, Pu, Xiao, Gao, Mingqi, Wan, Xiaojun, Zhu, Yuesheng
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation
por: Ruan, Jie, et al.
Publicado: (2024)

LLM-based NLG Evaluation: Current Status and Challenges
por: Gao, Mingqi, et al.
Publicado: (2024)

A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability
por: Hu, Xinyu, et al.
Publicado: (2025)

Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
por: Gao, Mingqi, et al.
Publicado: (2024)

Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators
por: Chang, Jiayi, et al.
Publicado: (2025)

Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability
por: Hu, Xinyu, et al.
Publicado: (2024)

Are LLM-based Evaluators Confusing NLG Quality Criteria?
por: Hu, Xinyu, et al.
Publicado: (2024)

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
por: Gao, Mingqi, et al.
Publicado: (2024)

Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too
por: Lawrence, Logan, et al.
Publicado: (2025)

A Systematic Review of Data-to-Text NLG
por: Osuji, Chinonso Cynthia, et al.
Publicado: (2024)

ConFu: Contemplate the Future for Better Speculative Sampling
por: Qin, Zongyue, et al.
Publicado: (2026)

Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective
por: Bai, Xueying, et al.
Publicado: (2024)

Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
por: Hong, Yuzhong, et al.
Publicado: (2024)

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
por: Li, Xueyan, et al.
Publicado: (2025)

Repeat After Me: Transformers are Better than State Space Models at Copying
por: Jelassi, Samy, et al.
Publicado: (2024)

Large Language Models Are Active Critics in NLG Evaluation
por: Xu, Shuying, et al.
Publicado: (2024)

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
por: Kim, Junseok, et al.
Publicado: (2026)

Constrained Adaptive Rejection Sampling
por: Parys, Paweł, et al.
Publicado: (2025)

TRA: Better Length Generalisation with Threshold Relative Attention
por: Opper, Mattia, et al.
Publicado: (2025)

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
por: Huo, Yifu, et al.
Publicado: (2026)

Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment
por: Ma, Xiang, et al.
Publicado: (2026)

$p1$: Better Prompt Optimization with Fewer Prompts
por: Gao, Zhaolin, et al.
Publicado: (2026)

Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques
por: Shaik, Rahimanuddin, et al.
Publicado: (2024)

Stabilizing Policy Optimization via Logits Convexity
por: Chen, Hongzhan, et al.
Publicado: (2026)

Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
por: Arias, Esteban Garces, et al.
Publicado: (2024)

OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
por: Song, Haiyue, et al.
Publicado: (2026)

Reliability Under Randomness: An Empirical Analysis of Sparse and Dense Language Models Across Decoding Temperatures
por: Grover, Kabir
Publicado: (2026)

Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference
por: Qiu, Wenjie, et al.
Publicado: (2025)

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
por: Yao, Kai, et al.
Publicado: (2024)

Deep Prompt Multi-task Network for Abuse Language Detection
por: Zhu, Jian, et al.
Publicado: (2024)

Learning to Learn for Few-shot Continual Active Learning
por: Ho, Stella, et al.
Publicado: (2023)

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
por: Ma, Qiyao, et al.
Publicado: (2026)

Smaller Language Models are Better Black-box Machine-Generated Text Detectors
por: Mireshghallah, Niloofar, et al.
Publicado: (2023)

Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages
por: Rohera, Pritika, et al.
Publicado: (2025)

PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning
por: Xiang, Hui, et al.
Publicado: (2025)

Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
por: Feng, Kehua, et al.
Publicado: (2024)

Active Preference Optimization for Sample Efficient RLHF
por: Das, Nirjhar, et al.
Publicado: (2024)

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
por: Wan, Xingchen, et al.
Publicado: (2024)

Reliable Evaluation and Benchmarks for Statement Autoformalization
por: Poiroux, Auguste, et al.
Publicado: (2024)

Data or Language Supervision: What Makes CLIP Better than DINO?
por: Liu, Yiming, et al.
Publicado: (2025)