Daily Archive
Updated from current HFEPX corpus (Feb 27, 2026). 15 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Frequently cited benchmark: Retrieval. Common metric signal: accuracy. 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 Nov 15, 2025.
Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 15 papers for HFEPX Fortnight Archive: 2025-F23. Dominant protocol signals include automatic metrics, simulation environments, with frequent benchmark focus on Retrieval, Cv-Bench and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.
20% of papers report explicit human-feedback signals, led by critique/edit feedback.
Evidence: Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , Error-Aware Knowledge Distillation via Targeted Revision for Customer-Service Summarization , EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation
automatic metrics appears in 93.3% of papers in this hub.
Evidence: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Mastering Olympiad-Level Physics with Artificial Intelligence , Chain of Summaries: Summarization Through Iterative Questioning
Retrieval is a recurring benchmark anchor for cross-paper comparisons in this page.
Evidence: CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces , EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
Quality-control reporting is sparse in this slice; prioritize papers with explicit calibration or adjudication steps.
Evidence: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , Mastering Olympiad-Level Physics with Artificial Intelligence
Rater context is mostly domain experts, and annotation is commonly mixed annotation units; use this to scope replication staffing.
Evidence: Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Mastering Olympiad-Level Physics with Artificial Intelligence
Stratify by benchmark (Retrieval vs Cv-Bench) before comparing methods.
Evidence: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , Mastering Olympiad-Level Physics with Artificial Intelligence
Papers with explicit human feedback
Coverage is a replication risk (20% vs 45% target).
Papers reporting quality controls
Coverage is a replication risk (0% vs 30% target).
Papers naming benchmarks/datasets
Coverage is strong (53.3% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (60% vs 35% target).
Papers with known rater population
Coverage is a replication risk (6.7% vs 35% target).
Papers with known annotation unit
Coverage is a replication risk (0% vs 35% target).
1. EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
Start here for detailed protocol reporting, including rater and quality-control evidence.
Start here for detailed protocol reporting, including rater and quality-control evidence.
Start here for detailed protocol reporting, including rater and quality-control evidence.
4. Mastering Olympiad-Level Physics with Artificial Intelligence
Adds automatic metrics for broader coverage within this hub.
5. Chain of Summaries: Summarization Through Iterative Questioning
Adds automatic metrics for broader coverage within this hub.
6. State of the Art in Text Classification for South Slavic Languages: Fine-Tuning or Prompting?
Adds automatic metrics for broader coverage within this hub.
7. Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Adds automatic metrics for broader coverage within this hub.
8. Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Adds automatic metrics for broader coverage within this hub.
automatic_metrics vs simulation_env
both=0, left_only=14, right_only=1
0 papers use both Automatic Metrics and Simulation Env.
Benchmark Brief
Retrieval
Coverage: 3 papers (20%)
3 papers (20%) mention Retrieval.
Examples: CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions , Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Benchmark Brief
Cv-Bench
Coverage: 1 papers (6.7%)
1 papers (6.7%) mention Cv-Bench.
Examples: Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
Benchmark Brief
MATH
Coverage: 1 papers (6.7%)
1 papers (6.7%) mention MATH.
Examples: Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
Metric Brief
accuracy
Coverage: 6 papers (40%)
6 papers (40%) mention accuracy.
Examples: CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Intelligence per Watt: Measuring Intelligence Efficiency of Local AI , Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents
Metric Brief
cost
Coverage: 2 papers (13.3%)
2 papers (13.3%) mention cost.
Examples: Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models , Error-Aware Knowledge Distillation via Targeted Revision for Customer-Service Summarization
Metric Brief
latency
Coverage: 2 papers (13.3%)
2 papers (13.3%) mention latency.
Examples: Intelligence per Watt: Measuring Intelligence Efficiency of Local AI , OckBench: Measuring the Efficiency of LLM Reasoning
Most Cited In This Hub
Fast path to methods with the strongest citation traction in this scope.
Papers: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
Most Recent
Fast path to latest protocol changes and newly published evaluation setups.
Papers: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
Best Protocol Detail
Papers with explicit rater/unit metadata and quality-control signals for reproducibility.
Papers: EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation , CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation , Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
Jiahe Shi, Zhengqi Gao, Ching-Yun Ko, Duane Boning · Nov 15, 2025
Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code.
Crystal Min Hui Poon, Pai Chet Ng, Xiaoxiao Miao, Immanuel Jun Kai Loh, Bowen Zhang · Nov 14, 2025
Instruction-guided text-to-speech (TTS) research has reached a maturity level where excellent speech generation quality is possible on demand, yet two coupled biases persist in reducing perceived quality: accent bias, where models default t
Mengze Hong, Di Jiang, Weiwei Zhao, Yawen Li, Yihang Wang · Nov 14, 2025
Experimental results highlight the effectiveness of the proposed system in generating more comprehensive and useful reviews aligned with expert standards, surpassing ablated baselines and advancing transparent, human-centered scholarly assi
Dong-Shan Jian, Xiang Li, Chen-Xu Yan, Hui-Wen Zheng, Zhi-Zhang Bian · Nov 13, 2025
Olympiad-level physics problem-solving significantly challenges both humans and artificial intelligence (AI), as it requires integrating appropriate modeling, application of physical principles, and precise calculation within long reasoning
William Brach, Kristián Košťál, Lukas Galke Poech · Nov 12, 2025
CoS thus resembles an appealing option for website maintainers to make their content more accessible for LLMs, while retaining possibilities for human oversight.
Taja Kuzman Pungeršek, Peter Rupnik, Ivan Porupski, Vuk Dinić, Nikola Ljubešić · Nov 11, 2025
Until recently, fine-tuned BERT-like models provided state-of-the-art performance on text classification tasks.
Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin, J. Wes Griffin, Herumb Shandilya · Nov 11, 2025
Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure.
Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury · Nov 10, 2025
On the Episodic Memory Benchmark (EpBench) \cite{huet_episodic_2025} comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to \textbf{20\%}.
Hanlin Cai, Houtianfu Wang, Haofan Dong, Kai Li, Sai Zou · Nov 10, 2025
Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale.
Haofeng Wang, Yu Zhang · Nov 10, 2025
Large Vision-Language Models (LVLMs) excel in multimodal reasoning and have shown impressive performance on various multimodal benchmarks.
Zheng Du, Hao Kang, Song Han, Tushar Krishna, Ligeng Zhu · Nov 7, 2025
Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage.
David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu · Nov 7, 2025
We introduce a framework able to synthesize vision-centric problems spanning diverse levels of complexity, and the resulting dataset with over 1M high-quality problems including: reasoning traces, preference data, and instruction prompts su
Saurabh Srivastava, Janit Bidhan, Hao Yan, Abhishek Dey, Tanu Kansal · Nov 6, 2025
Across 13 diverse benchmarks with DeepSeek-R1 and OpenAI-o1, batch prompting {reduces reasoning tokens by 76\% (2{,}950$\mapsto$710), on average, while preserving or improving accuracy}.
Hee-Jin Lee, Zhen Guo, Luchao Jin, Morteza Moazami Goudarzi · Nov 4, 2025
We introduce an Analyze-Revise-Finetune (ARF) pipeline that enables smaller open-source language models (LLMs) to surpass substantially larger proprietary models in customer service summarization tasks.
Soufiane Hayou · Nov 3, 2025
We provide the first proof of learning rate transfer with width in a linear multi-layer perceptron (MLP) parametrized with $μ$P, a neural network parameterization designed to ``maximize'' feature learning in the infinite-width limit.
