Metric Hub
Updated from current HFEPX corpus (Feb 27, 2026). 20 papers are grouped in this metric page. Common evaluation modes: Automatic Metrics, Simulation Env. Frequent quality control: Calibration. Frequently cited benchmark: Retrieval. Common metric signal: recall. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Feb 26, 2026.
Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 20 papers for Recall + General Metric Papers. Dominant protocol signals include automatic metrics, simulation environments, with frequent benchmark focus on Retrieval, Medieval and metric focus on recall, f1. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.
5% of papers report explicit human-feedback signals, led by pairwise preferences.
Evidence: MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks , Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access
automatic metrics appears in 95% of papers in this hub.
Evidence: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access , Towards Controllable Video Synthesis of Routine and Rare OR Events
Retrieval is a recurring benchmark anchor for cross-paper comparisons in this page.
Evidence: Personalized Graph-Empowered Large Language Model for Proactive Information Access , E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications , RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering , RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering
Most common quality-control signal is rater calibration (5% of papers).
Evidence: WISE: Web Information Satire and Fakeness Evaluation , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Probing for Knowledge Attribution in Large Language Models , Personalized Graph-Empowered Large Language Model for Proactive Information Access
Stratify by benchmark (Retrieval vs Medieval) before comparing methods.
Evidence: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access , Towards Controllable Video Synthesis of Routine and Rare OR Events
Track metric sensitivity by reporting both recall and f1.
Evidence: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access , Towards Controllable Video Synthesis of Routine and Rare OR Events
Papers with explicit human feedback
Coverage is a replication risk (5% vs 45% target).
Papers reporting quality controls
Coverage is a replication risk (10% vs 30% target).
Papers naming benchmarks/datasets
Coverage is strong (40% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (100% vs 35% target).
Papers with known rater population
Coverage is a replication risk (0% vs 35% target).
Papers with known annotation unit
Coverage is a replication risk (0% vs 35% target).
1. Probing for Knowledge Attribution in Large Language Models
Start here for detailed protocol reporting, including rater and quality-control evidence.
Start here for detailed protocol reporting, including rater and quality-control evidence.
3. Personalized Graph-Empowered Large Language Model for Proactive Information Access
Start here for detailed protocol reporting, including rater and quality-control evidence.
4. Towards Controllable Video Synthesis of Routine and Rare OR Events
Adds automatic metrics for broader coverage within this hub.
5. E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications
Adds automatic metrics for broader coverage within this hub.
6. Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams
Adds automatic metrics for broader coverage within this hub.
7. PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification
Adds automatic metrics for broader coverage within this hub.
8. Uncovering Context Reliance in Unstructured Knowledge Editing
Adds automatic metrics for broader coverage within this hub.
automatic_metrics vs simulation_env
both=2, left_only=17, right_only=1
2 papers use both Automatic Metrics and Simulation Env.
Benchmark Brief
Retrieval
Coverage: 6 papers (30%)
6 papers (30%) mention Retrieval.
Examples: Personalized Graph-Empowered Large Language Model for Proactive Information Access , E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications , RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
Benchmark Brief
Medieval
Coverage: 1 papers (5%)
1 papers (5%) mention Medieval.
Examples: Symphonym: Universal Phonetic Embeddings for Cross-Script Name Matching
Benchmark Brief
Memoryarena
Coverage: 1 papers (5%)
1 papers (5%) mention Memoryarena.
Examples: MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Metric Brief
recall
Coverage: 20 papers (100%)
20 papers (100%) mention recall.
Examples: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access
Metric Brief
f1
Coverage: 8 papers (40%)
8 papers (40%) mention f1.
Examples: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams
Metric Brief
precision
Coverage: 5 papers (25%)
5 papers (25%) mention precision.
Examples: A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams , PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification
Most Cited In This Hub
Fast path to methods with the strongest citation traction in this scope.
Papers: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access
Most Recent
Fast path to latest protocol changes and newly published evaluation setups.
Papers: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access
Best Protocol Detail
Papers with explicit rater/unit metadata and quality-control signals for reproducibility.
Papers: Probing for Knowledge Attribution in Large Language Models , A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection , Personalized Graph-Empowered Large Language Model for Proactive Information Access
Ivo Brink, Alexander Boer, Dennis Ulmer · Feb 26, 2026
Probes trained on AttriWiki data reveal a strong attribution signal, achieving up to 0.96 Macro-F1 on Llama-3.1-8B, Mistral-7B, and Qwen-7B, transferring to out-of-domain benchmarks (SQuAD, WebQuestions) with 0.94-0.99 Macro-F1 without retr
Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Rahat Uddin Azad, Saydul Akbar Murad · Feb 25, 2026
Evaluation uses multiple metrics, including accuracy, precision, recall, F1-score, Hamming loss, Cohens kappa, and AUC-ROC.
Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen · Feb 25, 2026
Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential.
Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri, Vishalroshan Anil, Aiza Maksutova · Feb 24, 2026
Purpose: Curating large-scale datasets of operating room (OR) workflow, encompassing rare, safety-critical, or atypical events, remains operationally and ethically challenging.
Jiwoo Kang, Yeon-Chang Lee · Feb 24, 2026
Multimodal recommender systems (MMRSs) enhance collaborative filtering by leveraging item-side modalities, but their reliance on a fixed set of modalities and task-specific objectives limits both modality extensibility and task generalizati
Darvan Shvan Khairaldeen, Hossein Hassani · Feb 24, 2026
On the full 50-song evaluation at a 0.750 threshold, recall was 39.4% and precision 25.8% .
Isun Chehreh, Ebrahim Ansari · Feb 22, 2026
Data collection involved 60,000 raw posts from various Persian social media platforms, followed by rigorous preprocessing and hybrid annotation combining ChatGPT-based few-shot prompting with human verification.
Zisheng Zhou, Mengqi Zhang, Shiguang Wu, Xiaotian Ye, Chi Zhang · Feb 22, 2026
Evaluations show that COIN reduces Context Reliance by 45.2% and outperforms strong baselines by 23.6% in editing success rate, highlighting the vital role of mitigating Context Reliance for robust editing.
Deniz Qian, Hung-Ting Chen, Eunsol Choi · Feb 20, 2026
Our method outperforms baselines, including agentic search approaches, achieving at least 10% relative and 3% absolute gain in complete recall percentage on a multi-answer retrieval dataset (QAMPARI).
Muhammad Tayyab Khan, Lequn Chen, Wenhe Feng, Seung Ki Moon · Feb 20, 2026
When deterministic scoring cannot resolve an ambiguity, the system escalates to multimodal and constrained large-language-model reasoning, followed by a single human-in-the-loop (HITL) review step.
Jyotin Goel, Souvik Maji, Pratik Mazumder · Feb 19, 2026
Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates.
Yiming Zhang, Siyue Zhang, Junbo Zhao, Chen Zhao · Feb 19, 2026
We evaluate RPDR on two long-tail retrieval benchmarks, PopQA and EntityQuestion, demonstrating substantial improvements over existing retrievers like BM25 and Contriver, especially on extremely long-tail categories.
Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen · Feb 18, 2026
Existing evaluations of agents with memory typically assess memorization and action in isolation.
Kexin Ma, Bojun Li, Yuhua Tang, Liting Sun, Ruochun Jin · Jan 14, 2026
Episodic memory is a central component of human memory, which refers to the ability to recall coherent events grounded in who, when, and where.
Stephen Gadd · Jan 11, 2026
Linking names across historical sources, languages, and writing systems remains a fundamental challenge in digital humanities and geographic information retrieval.
Gaurab Chhetri, Subasish Das, Tausif Islam Chowdhury · Dec 30, 2025
This study develops WISE (Web Information Satire and Fakeness Evaluation) framework which benchmarks eight lightweight transformer models alongside two baseline models on a balanced dataset of 20,000 samples from Fakeddit, annotated as eith
Mohammad Tavakoli, Alireza Salemi, Carrie Ye, Mohamed Abdalla, Hamed Zamani · Oct 31, 2025
Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coh
Anthony Hughes, Vasisht Duddu, N. Asokan, Nikolaos Aletras, Ning Ma · Oct 8, 2025
Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference.
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma, Christoph Riedl, Yonatan Belinkov · May 20, 2025
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality?
Rahul Garg, Trilok Padhi, Hemang Jain, Ugur Kursuncu, Ponnurangam Kumaraguru · Nov 19, 2024
Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively.
