- Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu · Feb 28, 2025
Red Team
To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues.
- The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
Shir Ashury-Tahan, Yifan Mai, Rajmohan C, Ariel Gera, Yotam Perlitz · Feb 26, 2025
To address this gap, we create ToRR, a benchmark for Table Reasoning and Robustness, measuring model performance and robustness on table-related tasks.
- Compressing Language Models for Specialized Domains
Miles Williams, George Chrysostomou, Vitor Jeronymo, Nikolaos Aletras · Feb 25, 2025
Compression techniques such as pruning and quantization offer a practical path towards efficient LM deployment, exemplified by their ability to preserve performance on general-purpose benchmarks.
- PII-Bench: Evaluating Query-Aware Privacy Protection Systems
Hao Shen, Zhouhong Gu, Haokai Hong, Weili Han · Feb 25, 2025
To address this challenge, we propose a query-unrelated PII masking strategy and introduce PII-Bench, the first comprehensive evaluation framework for assessing privacy protection systems.
- Can Multimodal LLMs Perform Time Series Anomaly Detection?
Xiongxiao Xu, Haoran Wang, Yueqing Liang, Philip S. Yu, Yue Zhao · Feb 25, 2025
Multi Agent
One natural way for humans to detect time series anomalies is through visualization and textual description.
- Bridging Gaps in Natural Language Processing for Yorùbá: A Systematic Review of a Decade of Progress and Prospects
Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov · Feb 24, 2025
Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human language looks indispensable.
- Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen · Feb 24, 2025
Pairwise Preference
Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval.
- Moving Beyond Medical Exams: A Clinician-Annotated Fairness Dataset of Real-World Tasks and Ambiguity in Mental Healthcare
Max Lamparth, Declan Grabb, Amy Franks, Scott Gershan, Kaitlyn N. Kunstman · Feb 22, 2025
Pairwise PreferenceExpert Verification
Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.
- Glycemic-Aware and Architecture-Agnostic Training Framework for Blood Glucose Forecasting in Type 1 Diabetes
Saman Khamesian, Asiful Arefeen, Maria Adela Grando, Bithika M. Thompson, Hassan Ghasemzadeh · Feb 20, 2025
Managing Type 1 Diabetes (T1D) demands constant vigilance as individuals strive to regulate their blood glucose levels and avoid dysglycemia, including hyperglycemia and hypoglycemia.
- SEFL: A Framework for Generating Synthetic Educational Assignment Feedback with LLM Agents
Mike Zhang, Amalie Pernille Dilling, Léon Gondelman, Niels Erik Ruan Lyngdorf, Euan D. Lindsay · Feb 18, 2025
Critique Edit
Through comprehensive evaluations with three LLM judges and three human experts, across a subset of 900 outputs, we demonstrate that SEFL-tuned models outperform both their untuned counterparts and an existing baseline in terms of feedback
- Using the Path of Least Resistance to Explain Deep Networks
Sina Salek, Joseph Enguehard · Feb 17, 2025
Through experiments on both synthetic and real-world image classification data, we provide empirical evidence supporting our theoretical analysis and showing that GIG produces more faithful attributions than existing methods, including IG,
- MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
Yuchen Yan, Yongliang Shen, Yang Liu, Jin Jiang, Xin Xu · Feb 17, 2025
Through comprehensive experiments on multiple mathematical reasoning datasets, including MathInstruct, MetaMathQA and etc., we demonstrate that models trained on MathFimer-expanded data consistently outperform their counterparts trained on
- Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
Bettina Messmer, Vinko Sabolčec, Martin Jaggi · Feb 14, 2025
Training a 1B-parameter Llama model for 70B and 119B tokens, our approach can match the baseline MMLU score with as little as 15% of the training tokens, while also improving across other benchmarks and mitigating the curse of multilinguali
- MoEMba: A Mamba-based Mixture of Experts for High-Density EMG-based Hand Gesture Recognition
Mehran Shabanpour, Kasra Rad, Sadaf Khademi, Arash Mohammadi · Feb 9, 2025
High-Density surface Electromyography (HDsEMG) has emerged as a pivotal resource for Human-Computer Interaction (HCI), offering direct insights into muscle activities and motion intentions.
- Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Jonathan Laurent, André Platzer · Feb 7, 2025
Demonstrations Web Browsing
Large Language Models can solve a wide range of tasks from just a few examples, but they remain difficult to steer and lack a capability essential for building reliable software at scale: the modular composition of computations under enforc
- vCache: Verified Semantic Prompt Caching
Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron, Kyle Chu, Shu Liu · Feb 6, 2025
We release the vCache implementation and four benchmarks to support future research.
