Daily Archive
Updated from current HFEPX corpus (Feb 27, 2026). 18 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. 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 May 30, 2025.
Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 18 papers for HFEPX Fortnight Archive: 2025-F11. Dominant protocol signals include automatic metrics, simulation environments, with frequent benchmark focus on Retrieval, Rtc-Bench and metric focus on accuracy, context length. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.
27.8% of papers report explicit human-feedback signals, led by pairwise preferences.
Evidence: Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages , Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task , VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models , When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
automatic metrics appears in 88.9% of papers in this hub.
Evidence: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages , PonderLM: Pretraining Language Models to Ponder in Continuous Space
Retrieval is a recurring benchmark anchor for cross-paper comparisons in this page.
Evidence: Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task , Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability , When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
Quality-control reporting is sparse in this slice; prioritize papers with explicit calibration or adjudication steps.
Evidence: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages , RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Stratify by benchmark (Retrieval vs Rtc-Bench) before comparing methods.
Evidence: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages , RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Track metric sensitivity by reporting both accuracy and context length.
Evidence: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages , RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Papers with explicit human feedback
Coverage is usable but incomplete (27.8% vs 45% target).
Papers reporting quality controls
Coverage is a replication risk (0% vs 30% target).
Papers naming benchmarks/datasets
Coverage is usable but incomplete (27.8% vs 35% target).
Papers naming evaluation metrics
Coverage is strong (55.6% 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. When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
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. RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Adds simulation environments with red-team protocols for broader coverage within this hub.
5. PonderLM: Pretraining Language Models to Ponder in Continuous Space
Adds automatic metrics for broader coverage within this hub.
6. FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
Adds automatic metrics for broader coverage within this hub.
7. Knowledge Fusion of Large Language Models Via Modular SkillPacks
Adds automatic metrics for broader coverage within this hub.
8. HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning
Adds automatic metrics for broader coverage within this hub.
automatic_metrics vs simulation_env
both=1, left_only=15, right_only=2
1 papers use both Automatic Metrics and Simulation Env.
Benchmark Brief
Retrieval
Coverage: 3 papers (16.7%)
3 papers (16.7%) mention Retrieval.
Examples: Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task , Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability
Benchmark Brief
Rtc-Bench
Coverage: 1 papers (5.6%)
1 papers (5.6%) mention Rtc-Bench.
Examples: RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Benchmark Brief
Verifybench
Coverage: 1 papers (5.6%)
1 papers (5.6%) mention Verifybench.
Examples: VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Metric Brief
accuracy
Coverage: 7 papers (38.9%)
7 papers (38.9%) mention accuracy.
Examples: Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning , On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
Metric Brief
context length
Coverage: 2 papers (11.1%)
2 papers (11.1%) mention context length.
Examples: Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
Metric Brief
jailbreak success rate
Coverage: 1 papers (5.6%)
1 papers (5.6%) mention jailbreak success rate.
Examples: RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Most Cited In This Hub
Fast path to methods with the strongest citation traction in this scope.
Papers: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages
Most Recent
Fast path to latest protocol changes and newly published evaluation setups.
Papers: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages
Best Protocol Detail
Papers with explicit rater/unit metadata and quality-control signals for reproducibility.
Papers: When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations , Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation , Counting trees: A treebank-driven exploration of syntactic variation in speech and writing across languages
Kailin Jiang, Yuntao Du, Yukai Ding, Yuchen Ren, Ning Jiang · May 30, 2025
To address this, we first propose a pipeline to construct MMEVOKE, a benchmark for evaluating LMMs' ability in multimodal evolving knowledge injection.
Arthur S. Bianchessi, Yasmin C. Aguirre, Rodrigo C. Barros, Lucas S. Kupssinskü · May 28, 2025
However, existing PE methods lack theoretical clarity and rely on limited evaluation metrics to substantiate their extrapolation claims.
Kaja Dobrovoljc · May 28, 2025
Results show that, across both languages, spoken corpora contain fewer and less diverse syntactic structures than their written counterparts, with consistent cross-linguistic preferences for certain structural types across modalities.
Zeyi Liao, Jaylen Jones, Linxi Jiang, Yuting Ning, Eric Fosler-Lussier · May 28, 2025
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection.
Boyi Zeng, Shixiang Song, Siyuan Huang, Yixuan Wang, He Li · May 27, 2025
Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort.
Yan Wang, Lingfei Qian, Xueqing Peng, Yang Ren, Keyi Wang · May 27, 2025
Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents.
Guodong Du, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi · May 24, 2025
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning.
Chuhao Zhou, Jianfei Yang · May 23, 2025
Embodied agents operating in smart homes must understand human behavior through diverse sensory inputs and communicate via natural language.
Yifan Zhang, Yifeng Liu, Huizhuo Yuan, Yang Yuan, Quanquan Gu · May 23, 2025
On mathematical reasoning benchmarks (AIME24, AIME25), RPG-REINFORCE with RPG-Style Clip improves accuracy by up to $+6$ absolute percentage points over DAPO.
Xinpeng Wang, Mingyang Wang, Yihong Liu, Hinrich Schütze, Barbara Plank · May 22, 2025
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety.
Punya Syon Pandey, Samuel Simko, Kellin Pelrine, Zhijing Jin · May 22, 2025
As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern.
Mengyang Qiu, Zoe Brisebois, Siena Sun · May 22, 2025
Large language models (LLMs) are increasingly explored as substitutes for human participants in cognitive tasks, but their ability to simulate human behavioral variability remains unclear.
Yuchen Yan, Jin Jiang, Zhenbang Ren, Yijun Li, Xudong Cai · May 21, 2025
However, existing reward benchmarks focus on preference comparisons between responses rather than evaluating verification against ground truth references, leaving a critical gap in our ability to evaluate verification systems used in reason
Gaurav Kumar, Ayush Garg, Debajyoti Mazumder, Aditya Kishore, Babu kumar · May 21, 2025
Automated fact-checking has been a challenging task for the research community.
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?
Oren Sultan, Eitan Stern, Dafna Shahaf · May 20, 2025
Large language models (LLMs) struggle with formal domains that require rigorous logical deduction and symbolic reasoning, such as mathematical proof generation.
Aswathy Velutharambath, Kai Sassenberg, Roman Klinger · May 19, 2025
We further benchmark against other English deception datasets following similar data collection protocols.
Chundra Cathcart · May 19, 2025
The numeral systems of Indo-Aryan languages such as Hindi, Gujarati, and Bengali are highly unusual in that unlike most numeral systems (e.g., those of English, Chinese, etc.), forms referring to 1--99 are highly non-transparent and are can
