Daily Archive
Updated from current HFEPX corpus (Feb 27, 2026). 8 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Calibration. Frequently cited benchmark: BrowseComp. Common metric signal: accuracy. Newest paper in this set is from Feb 13, 2026.
Updated from current HFEPX corpus (Feb 27, 2026). This page covers 8 papers centered on HFEPX Daily Archive: 2026-02-13. Common evaluation modes include Automatic Metrics, Simulation Env, with benchmark emphasis on BrowseComp, LMSYS Chatbot Arena. Use the anchored takeaways below to compare protocol choices and identify papers with stronger evidence depth.
Evaluation emphasis: Automatic Metrics and Simulation Env appear frequently in this slice.
Evidence: Semantic Chunking and the Entropy of Natural Language , OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report , SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Benchmark concentration: BrowseComp, LMSYS Chatbot Arena helps control cross-paper variance.
Evidence: OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report , SCOPE: Selective Conformal Optimized Pairwise LLM Judging , Towards interpretable models for language proficiency assessment: Predicting the CEFR level of Estonian learner texts
Metric concentration: accuracy, precision is repeatedly reported in this group.
Evidence: SCOPE: Selective Conformal Optimized Pairwise LLM Judging , Towards interpretable models for language proficiency assessment: Predicting the CEFR level of Estonian learner texts , Buy versus Build an LLM: A Decision Framework for Governments
Stratify by benchmark (BrowseComp vs LMSYS Chatbot Arena) before comparing methods.
Evidence: Towards interpretable models for language proficiency assessment: Predicting the CEFR level of Estonian learner texts , Buy versus Build an LLM: A Decision Framework for Governments , BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Track metric sensitivity by reporting both accuracy and precision.
Evidence: Buy versus Build an LLM: A Decision Framework for Governments , BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents , PMG: Parameterized Motion Generator for Human-like Locomotion Control
Papers with explicit human feedback is visible in approximately 12.5% of papers in this set.
Evidence: BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents , PMG: Parameterized Motion Generator for Human-like Locomotion Control , Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Papers with explicit human feedback
Coverage is a replication risk (12.5% vs 45% target).
Papers reporting quality controls
Coverage is usable but incomplete (25% vs 30% target).
Papers naming benchmarks/datasets
Coverage is usable but incomplete (25% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (87.5% vs 35% target).
Papers with known rater population
Coverage is a replication risk (12.5% vs 35% target).
Papers with known annotation unit
Coverage is usable but incomplete (25% vs 35% target).
1. Semantic Chunking and the Entropy of Natural Language
Start with this anchor paper for scope and protocol framing. Covers Automatic Metrics.
Covers Automatic Metrics.
3. SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Covers Automatic Metrics. Includes human-feedback signal: Pairwise Preference.
Covers Automatic Metrics, Simulation Env.
5. Buy versus Build an LLM: A Decision Framework for Governments
Covers Automatic Metrics.
6. BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Covers Automatic Metrics, Simulation Env.
7. PMG: Parameterized Motion Generator for Human-like Locomotion Control
Covers Automatic Metrics.
8. Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Covers Automatic Metrics.
automatic_metrics vs simulation_env
both=2, left_only=6, right_only=0
2 papers use both Automatic Metrics and Simulation Env.
Weishun Zhong, Doron Sivan, Tankut Can, Mikhail Katkov, Misha Tsodyks · Feb 13, 2026
The entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) have only recently approached.
Mariia Fedorova, Nikolay Arefyev, Maja Buljan, Jindřich Helcl, Stephan Oepen · Feb 13, 2026
We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks.
Sher Badshah, Ali Emami, Hassan Sajjad · Feb 13, 2026
Large language models (LLMs) are increasingly used as judges to replace costly human preference labels in pairwise evaluation.
Kais Allkivi · Feb 13, 2026
Additional evaluation on an earlier exam sample revealed that the writings have become more complex over a 7-10-year period, while accuracy still reached 0.8 with some feature sets.
Jiahao Lu, Ziwei Xu, William Tjhi, Junnan Li, Antoine Bosselut · Feb 13, 2026
This paper provides a strategic framework for making this decision by evaluating these options across dimensions including sovereignty, safety, cost, resource capability, cultural fit, and sustainability.
Huanyao Zhang, Jiepeng Zhou, Bo Li, Bowen Zhou, Yanzhe Shan · Feb 13, 2026
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimodal web browsing and deep search in open-world environments.
Chenxi Han, Yuheng Min, Zihao Huang, Ao Hong, Hang Liu · Feb 13, 2026
Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain.
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin · Feb 13, 2026
As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
