- VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modeling
Yanir Marmor, Arad Zulti, David Krongauz, Adam Gabet, Yoad Snapir · Mar 1, 2026 · Citations: 0
Speech processing systems face a fundamental challenge: the human voice changes with age, yet few datasets support rigorous longitudinal evaluation.
- A Study on Building Efficient Zero-Shot Relation Extraction Models
Hugo Thomas, Caio Corro, Guillaume Gravier, Pascale Sébillot · Mar 1, 2026 · Citations: 0
- Learn Hard Problems During RL with Reference Guided Fine-tuning
Yangzhen Wu, Shanda Li, Zixin Wen, Xin Zhou, Ameet Talwalkar · Mar 1, 2026 · Citations: 0
We introduce Reference-Guided Fine-Tuning (ReGFT), a simple and effective method that utilizes human-written reference solutions to synthesize positive trajectories on hard problems and train on them before RL.
- Reasoning Boosts Opinion Alignment in LLMs
Frédéric Berdoz, Yann Billeter, Yann Vonlanthen, Roger Wattenhofer · Mar 1, 2026 · Citations: 0
Pairwise Preference
Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital democracies, where models could help shape fairer and more popular policies.
- HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning
Bartosz Trojan, Filip Gębala · Mar 1, 2026 · Citations: 0
Evaluating across the GLUE benchmark, we demonstrate that LoRA-based adaptation consistently achieves calibration parity with (and in specific tasks exceeds) full fine-tuning, while maintaining significantly higher parameter efficiency.
- GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
Zhuokang Shen, Yifan Wang, Hanyu Chen, Yunhang Shen, Wenxuan Huang · Mar 1, 2026 · Citations: 0
- Conformal Prediction for Risk-Controlled Medical Entity Extraction Across Clinical Domains
Manil Shrestha, Edward Kim · Mar 1, 2026 · Citations: 0
First, we extract structured entities from 1,000 FDA drug labels across eight sections using GPT-4.1, verified via FactScore-based atomic statement evaluation (97.7\% accuracy over 128,906 entities).
- Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare
Shravani Hariprasad · Mar 1, 2026 · Citations: 0
- Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
Theophilus Amaefuna, Hitesh Vaidya, Anshuman Chhabra, Ankur Mali · Mar 1, 2026 · Citations: 0
- KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging
Lianjun Liu, Hongli An, Weiqi Yan, Xin Du, Shengchuan Zhang · Mar 1, 2026 · Citations: 0
Extensive experiments across various models and benchmarks demonstrate that KVSlimmer consistently outperforms SOTA methods.
- CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li · Mar 1, 2026 · Citations: 0
- Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact
Michael Hardy, Yunsung Kim · Mar 1, 2026 · Citations: 0
- BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning
Yuyang Liu, Jingya Wang, Liuzhenghao Lv, Yonghong Tian · Mar 1, 2026 · Citations: 0
- MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
Xuying Ning, Dongqi Fu, Tianxin Wei, Mengting Ai, Jiaru Zou · Mar 1, 2026 · Citations: 0
- PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecture
Jie Li, Shengwei Tian, Long Yu, Xin Ning · Mar 1, 2026 · Citations: 0
- MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine
Kai Zhang, Zhengqing Yuan, Cheng Peng, Songlin Zhao, Mengxian Lyu · Mar 1, 2026 · Citations: 0
- Learning Nested Named Entity Recognition from Flat Annotations
Igor Rozhkov, Natalia Loukachevitch · Feb 28, 2026 · Citations: 0
- Constitutional Black-Box Monitoring for Scheming in LLM Agents
Simon Storf, Rich Barton-Cooper, James Peters-Gill, Marius Hobbhahn · Feb 28, 2026 · Citations: 0
- A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
Hossein Javidnia · Feb 28, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction
Ruihao Pan, Suhang Wang · Feb 28, 2026 · Citations: 0
Machine unlearning aims to remove the influence of specific training data from pre-trained models without retraining from scratch, and is increasingly important for large language models (LLMs) due to safety, privacy, and legal concerns.
- Qwen3-Coder-Next Technical Report
Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, Yunlong Feng · Feb 28, 2026 · Citations: 0
- LaSTR: Language-Driven Time-Series Segment Retrieval
Kota Dohi, Harsh Purohit, Tomoya Nishida, Takashi Endo, Yusuke Ohtsubo · Feb 28, 2026 · Citations: 0
- RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen, Yidong Wang, Yu Luo · Feb 28, 2026 · Citations: 0
- SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
Shiqi Chen, Jingze Gai, Ruochen Zhou, Jinghan Zhang, Tongyao Zhu · Feb 28, 2026 · Citations: 0
Long Horizon
Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool…
- DRIV-EX: Counterfactual Explanations for Driving LLMs
Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Eric Gaussier · Feb 28, 2026 · Citations: 0
- RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis
Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Bosi Wen, Yidong Wang · Feb 28, 2026 · Citations: 0
- Polynomial Mixing for Efficient Self-supervised Speech Encoders
Eva Feillet, Ryan Whetten, David Picard, Alexandre Allauzen · Feb 28, 2026 · Citations: 0
- SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs
Chaoyue He, Xin Zhou, Xinjia Yu, Lei Zhang, Yan Zhang · Feb 28, 2026 · Citations: 0
Expert Verification
We present SSKG Hub (Sustainability Standards Knowledge Graph Hub), a research prototype and interactive web platform that transforms standards into auditable knowledge graphs (KGs) through an LLM-centered, expert-guided pipeline.
- BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages
Jason Lucas, Matt Murtagh-White, Adaku Uchendu, Ali Al-Lawati, Michiharu Yamashita · Feb 28, 2026 · Citations: 0
Multi Agent
We introduce BLUFF, a comprehensive benchmark for detecting false and synthetic content, spanning 79 languages with over 202K samples, combining human-written fact-checked content (122K+ samples across 57 languages) and LLM-generated…
- TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
Shu-Xun Yang, Cunxiang Wang, Haoke Zhang, Wenbo Yu, Lindong Wu · Feb 28, 2026 · Citations: 0
- Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification
Anastasia Zhukova, Terry Ruas, Jan Philip Wahle, Bela Gipp · Feb 28, 2026 · Citations: 0
To address these challenges, we introduce uCDCR, a unified dataset that consolidates diverse publicly available English CDCR corpora across various domains into a consistent format, which we analyze with standardized metrics and evaluation…
- QQ: A Toolkit for Language Identifiers and Metadata
Wessel Poelman, Yiyi Chen, Miryam de Lhoneux · Feb 28, 2026 · Citations: 0
- From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation
Raneen Younis, Suvinava Basak, Lukas Chavez, Zahra Ahmadi · Feb 28, 2026 · Citations: 0
- LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
Yuchen Hou, Lin Zhao · Feb 28, 2026 · Citations: 0
- Super Research: Answering Highly Complex Questions with Large Language Models through Super Deep and Super Wide Research
Yubo Dong, Nianhao You, Yuxuan Hou, Zixun Sun, Yue Zhang · Feb 28, 2026 · Citations: 0
Long Horizon
To evaluate this capability, we curated a benchmark of 300 expert-written questions across diverse domains, each requiring up to 100+ retrieval steps and 1,000+ web pages to reconcile conflicting evidence.
- Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
Jie Cao, Tianwei Lin, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao · Feb 28, 2026 · Citations: 0
- CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao · Feb 28, 2026 · Citations: 0
- CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
Swapnil Parekh · Feb 28, 2026 · Citations: 0
- Optimizing In-Context Demonstrations for LLM-based Automated Grading
Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Kevin Haudek · Feb 28, 2026 · Citations: 0
Rubric RatingDemonstrations
GUIDE paves the way for trusted, scalable assessment systems that align closely with human pedagogical standards.
- Confusion-Aware Rubric Optimization for LLM-based Automated Grading
Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Joseph Krajcik · Feb 28, 2026 · Citations: 0
Rubric Rating
Empirical evaluations on teacher education and STEM datasets demonstrate that CARO significantly outperforms existing SOTA methods.
- RTLocating: Intent-aware RTL Localization for Hardware Design Iteration
Changwen Xing, Yanfeng Lu, Lei Qi, Chenxu Niu, Jie Li · Feb 28, 2026 · Citations: 0
- A Typologically Grounded Evaluation Framework for Word Order and Morphology Sensitivity in Multilingual Masked LMs
Anna Feldman, Libby Barak, Jing Peng · Feb 28, 2026 · Citations: 0
- LLM-Bootstrapped Targeted Finding Guidance for Factual MLLM-based Medical Report Generation
Cunyuan Yang, Dejuan Song, Xiaotao Pang, Qianqian Shen, Wenjie Nie · Feb 28, 2026 · Citations: 0
- Policy Compliance of User Requests in Natural Language for AI Systems
Pedro Cisneros-Velarde · Feb 27, 2026 · Citations: 0
- Distribution-Aware Companding Quantization of Large Language Models
Athul Radhakrishnan, Siddhant Mohan, Mahima Sachdeva · Feb 27, 2026 · Citations: 0
- How Large Language Models Get Stuck: Early structure with persistent errors
Alokesh Manna, William Snyder, Whitney Tabor · Feb 27, 2026 · Citations: 0
Pairwise Preference
We trained Meta's OPT model on the 100M word BabyLM dataset, and evaluated it on the BLiMP benchmark, which consists of 67 classes, each defined by sentence pairs that differ in a targeted syntactic or semantic rule violation.
- Brittlebench: Quantifying LLM robustness via prompt sensitivity
Angelika Romanou, Mark Ibrahim, Candace Ross, Chantal Shaib, Kerem Oktar · Feb 27, 2026 · Citations: 0
- When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation
Bian Sun, Zhenjian Wang, Orvill de la Torre, Zirui Wang · Feb 27, 2026 · Citations: 0
Due to the resource-intensive nature of large-scale human validation, the model's performance was evaluated through a dual-track framework: Track A utilized traditional lexical similarity metrics (e.g., BLEU, ROUGE), while Track B employed…
- From Prerequisites to Predictions: Validating a Geometric Hallucination Taxonomy Through Controlled Induction
Matic Korun · Feb 27, 2026 · Citations: 0
- Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li · Feb 27, 2026 · Citations: 0
Long Horizon
Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy.
- Transformers Remember First, Forget Last: Dual-Process Interference in LLMs
Sourav Chattaraj, Kanak Raj · Feb 27, 2026 · Citations: 0
Every model shows the same pattern: proactive interference (PI) dominates retroactive interference (RI) universally (Cohen's d = 1.73, p < 0.0001), meaning early encodings are protected at the cost of recent information -- the opposite of…
- DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
Fan Shu, Yite Wang, Ruofan Wu, Boyi Liu, Zhewei Yao · Feb 27, 2026 · Citations: 0
Long Horizon
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking.
- Do LLMs Benefit From Their Own Words?
Jenny Y. Huang, Leshem Choshen, Ramon Astudillo, Tamara Broderick, Jacob Andreas · Feb 27, 2026 · Citations: 0
- Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan · Feb 27, 2026 · Citations: 0
- A Minimal Agent for Automated Theorem Proving
Borja Requena, Austin Letson, Krystian Nowakowski, Izan Beltran Ferreiro, Leopoldo Sarra · Feb 27, 2026 · Citations: 0
- Controllable Reasoning Models Are Private Thinkers
Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych · Feb 27, 2026 · Citations: 0
- Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low · Feb 27, 2026 · Citations: 0
- MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
Jacob Eisenstein, Fantine Huot, Adam Fisch, Jonathan Berant, Mirella Lapata · Feb 27, 2026 · Citations: 0
- Task-Centric Acceleration of Small-Language Models
Dor Tsur, Sharon Adar, Ran Levy · Feb 27, 2026 · Citations: 0
- ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models
Adam Dejl, Deniz Gorur, Francesca Toni · Feb 27, 2026 · Citations: 0
Demonstrations
Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the resulting decisions faithfully explainable to and contestable by…