Papers
When Models Hesitate: Answer Instability as a Label-Free Uncertainty Signal for LLMs
Jasper Meynard Arana, Kristine Ann M. Carandang, Ethan Robert Casin et al.
Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
Sercan Karakaş, Yusuf Şimşek
Conformal LLM Routing with Distribution-Free Safety Guarantees
Iqtedar Uddin, André Bauer
RegTrack: A Fine-Grained Benchmark for Multi-Class Legal Change Detection
Joe Yu, Kevin Chenhao Li, Julian Ostarek
Thesis Proposal: Self-Adaptive and Epistemic Uncertainty-Guided ASR of Dense Intra-Sentential Code-Switched Speech for African Low-Resource Languages
Umar Baba Umar, Sulaimon Adebayo Bashir, Abdulmalik Danlami Mohammed et al.
Fusion Training for Mathematical Generalization in Large Language Models
Congfeng Cao, Pengyu Zhang, Jelke Bloem
Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer
Ahmed Haj Ahmed, Ruochen Zhang, Alvin C Grissom II
Inference-Time Feedback for Reasoning Controllability in Diffusion Language Models
Clovis Barbour, Huixin Zhan
LAMP-MedQA: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering
Jack A. Johnson, Meghali Banerjee, Joseph Crawford et al.
CBAL: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement
Odwitiyo Dutta, Dinesh K Vishwakarma
Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment
Ria Talsania, Dhruv Ritesh Shah, Sudhir Dhage
Probing Bias Formation in Medical LLMs through Activation Steering
Bayram Ayadi, Annette Hautli-Janisz
From Graphs to Hypergraphs: Enhancing Aspect-Term Sentiment Analysis via Multi-Level Relational Modeling
Omkar Mahesh Kashyap, Padegal Amit, Madhav Kashyap et al.
Counterspeech Generation using Small Language Models
Abubakar Sadiq Muhammad, Simona Frenda, Gavin Abercrombie
A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
Michito Takeshita, Takuro Kawada, Takumi Ohashi et al.
Thesis Proposal: Targeted and Unified Cross-Lingual Unlearning from Multilingual Language Models
Jan Bronec, Jindřich Helcl
CAL-Log: Cost-Aware Active Learning with Logarithmic Cognitive Effort Modeling and Online Adaptation to Human Annotation Behavior
Vihanga Supasan Kariyakaranage, Banuka Athuraliya
Leakage-Aware User-Level ADHD Signal Classification from Social Media: When Graph Aggregation Helps, and When It Does Not
Daniel Cieślak, Władysław Średniawa
The Silence of the Facts: Popularity as a Barrier to Machine Unlearning
Anna Borisiuk, Andrey Savchenko, Alexander Panchenko et al.
Analyzing Hate Speech Amplification on Fringe Platforms
Anika Ghosh Basu, Humberto Jesus Carlon, Junyi Liu