- Mapping Semantic & Syntactic Relationships with Geometric Rotation
Michael Freenor, Lauren Alvarez · Oct 10, 2025 · Citations: 0
Demonstrations
We introduce Rotor-Invariant Shift Estimation (RISE), a geometric approach that represents semantic-syntactic transformations as consistent rotational operations in embedding space, leveraging the manifold structure of modern language…
- GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
Margarita Belova, Jiaxin Xiao, Shikhar Tuli, Niraj K. Jha · Oct 10, 2025 · Citations: 0
Expert Verification
GraphMERT + KG is the first efficient and scalable neurosymbolic model to achieve state-of-the-art benchmark accuracy along with superior symbolic representations relative to baselines.
- The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
Nizar El Ghazal, Antoine Caubrière, Valentin Vielzeuf · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Chlorophyll-a Mapping and Prediction in the Mar Menor Lagoon Using C2RCC-Processed Sentinel 2 Imagery
Antonio Martínez-Ibarra, Aurora González-Vidal, Adrián Cánovas-Rodríguez, Antonio F. Skarmeta · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination
Charidimos Papadakis, Angeliki Dimitriou, Giorgos Filandrianos, Maria Lymperaiou, Konstantinos Thomas · Oct 10, 2025 · Citations: 0
- Verifying Chain-of-Thought Reasoning via Its Computational Graph
Zheng Zhao, Yeskendir Koishekenov, Xianjun Yang, Naila Murray, Nicola Cancedda · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
Jiapeng Wang, Changxin Tian, Kunlong Chen, Ziqi Liu, Jiaxin Mao · Oct 10, 2025 · Citations: 0
Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics.
- Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Yongding Tao, Tian Wang, Yihong Dong, Huanyu Liu, Kechi Zhang · Oct 10, 2025 · Citations: 0
Critique Edit
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs).
- DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
Chenyang Gu, Yewen Pu, Bruce Yang, Xiaofan Li, Huan Gao · Oct 10, 2025 · Citations: 0
Demonstrations
Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance ceilings and collapse when applying RL to complex interactive tasks, leaving their true agentic potential untapped.
- Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation
Vijay M. Galshetwar, Praful Hambarde, Prashant W. Patil, Akshay Dudhane, Sachin Chaudhary · Oct 10, 2025 · Citations: 0
- Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Yumin Choi, Dongki Kim, Jinheon Baek, Sung Ju Hwang · Oct 10, 2025 · Citations: 0
To tackle this problem, we then propose the Multimodal Prompt Optimizer (MPO), a unified framework that not only performs the joint optimization of multimodal prompts through alignment-preserving updates but also guides the selection…
- A Linguistics-Aware LLM Watermarking via Syntactic Predictability
Shinwoo Park, Hyejin Park, Hyeseon Ahn, Yo-Sub Han · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness
Chi Seng Cheang, Hou Pong Chan, Wenxuan Zhang, Yang Deng · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models
Ruitong Liu, Boxu Lin, Peize Li, Siyuan Li, Yunjia Wu · Oct 10, 2025 · Citations: 0
- Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
Xin Liu, Runsong Zhao, Pengcheng Huang, Xinyu Liu, Junyi Xiao · Oct 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
Yan Wang, Keyi Wang, Shanshan Yang, Jaisal Patel, Jeff Zhao · Oct 10, 2025 · Citations: 0
We introduce FinAuditing, a taxonomy-aligned, structure-aware benchmark built from real XBRL filings.