- Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu · Feb 28, 2025 · Citations: 0
Red Team
To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues.
- Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf · Feb 28, 2025 · Citations: 0
- Prediction of Item Difficulty for Reading Comprehension Items by Creation of Annotated Item Repository
Radhika Kapoor, Sang T. Truong, Nick Haber, Maria Araceli Ruiz-Primo, Benjamin W. Domingue · Feb 28, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
Taiqiang Wu, Chenchen Ding, Wenyong Zhou, Yuxin Cheng, Xincheng Feng · Feb 27, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Stay Focused: Problem Drift in Multi-Agent Debate
Jonas Becker, Lars Benedikt Kaesberg, Andreas Stephan, Jan Philip Wahle, Terry Ruas · Feb 26, 2025 · Citations: 0
Multi Agent
Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks.
- The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
Shir Ashury-Tahan, Yifan Mai, Rajmohan C, Ariel Gera, Yotam Perlitz · Feb 26, 2025 · Citations: 0
To address this gap, we create ToRR, a benchmark for Table Reasoning and Robustness, measuring model performance and robustness on table-related tasks.
- Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
Hongyi Cai, Jie Li, Mohammad Mahdinur Rahman, Wenzhen Dong · Feb 26, 2025 · Citations: 0
Experimental evaluation demonstrates that models fine-tuned on LCG-filtered subsets of 6K samples achieve superior performance compared to existing methods, with substantial improvements on MT-bench and consistent gains across comprehensive…
- Transforming the Voice of the Customer: Large Language Models for Identifying Customer Needs
Artem Timoshenko, Chengfeng Mao, John R. Hauser · Feb 25, 2025 · Citations: 0
While current practice uses machine learning to screen content, the critical final step of precisely formulating CNs relies on expert human judgment.
- Compressing Language Models for Specialized Domains
Miles Williams, George Chrysostomou, Vitor Jeronymo, Nikolaos Aletras · Feb 25, 2025 · Citations: 0
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.
- Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
Ru Wang, Wei Huang, Selena Song, Haoyu Zhang, Qian Niu · Feb 25, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- PII-Bench: Evaluating Query-Aware Privacy Protection Systems
Hao Shen, Zhouhong Gu, Haokai Hong, Weili Han · Feb 25, 2025 · Citations: 0
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.
- Connecting Voices: LoReSpeech as a Low-Resource Speech Parallel Corpus
Samy Ouzerrout · Feb 25, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Can Multimodal LLMs Perform Time Series Anomaly Detection?
Xiongxiao Xu, Haoran Wang, Yueqing Liang, Philip S. Yu, Yue Zhao · Feb 25, 2025 · Citations: 0
Multi Agent
One natural way for humans to detect time series anomalies is through visualization and textual description.
- Renormalization-Inspired Effective Field Neural Networks for Scalable Modeling of Classical and Quantum Many-Body Systems
Xi Liu, Yujun Zhao, Chun Yu Wan, Yang Zhang, Junwei Liu · Feb 24, 2025 · Citations: 0
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang · Feb 24, 2025 · Citations: 0
As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…
- 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 · Citations: 0
Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human language looks indispensable.
- HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
Haolan Wang, Zhenghao Liu, Xinze Li, Xiaocui Yang, Yu Gu · Feb 24, 2025 · Citations: 0
Pairwise Preference
To better capture structural semantics from the tabular data, this paper introduces the HybrId-modal Preference oPtimizatiOn (HIPPO) model, which represents tables using both text and image, optimizing MLLMs by learning more comprehensive…
- Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
Chengyin Xu, Kaiyuan Chen, Xiao Li, Ke Shen, Chenggang Li · Feb 24, 2025 · Citations: 0
Predictable subset performance acts as an intermediate predictor for the full evaluation set.
- From Euler to AI: Unifying Formulas for Mathematical Constants
Tomer Raz, Michael Shalyt, Elyasheev Leibtag, Rotem Kalisch, Shachar Weinbaum · Feb 24, 2025 · Citations: 0
- Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen · Feb 24, 2025 · Citations: 0
Pairwise Preference
Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval.
- Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Chenghao Fan, Zhenyi Lu, Sichen Liu, Chengfeng Gu, Xiaoye Qu · Feb 24, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- 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 · Citations: 0
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.
- Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality
Iago Alves Brito, Julia Soares Dollis, Fernanda Bufon Färber, Pedro Schindler Freire Brasil Ribeiro, Rafael Teixeira Sousa · Feb 22, 2025 · Citations: 0
The integration of large language models (LLMs) into virtual reality (VR) environments has opened new pathways for creating more immersive and interactive digital humans.
- HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
Rasmus Aavang, Giovanni Rizzi, Rasmus Bøggild, Alexandre Iolov, Mike Zhang · Feb 21, 2025 · Citations: 0
For rapid evaluation, we also release HiFi-KPI-Lite, a manually curated 8K paragraph subset.
- Less is More: Improving LLM Alignment via Preference Data Selection
Xun Deng, Han Zhong, Rui Ai, Fuli Feng, Zheng Wang · Feb 20, 2025 · Citations: 0
Pairwise Preference
Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences.
- 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 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh
Nurkhan Laiyk, Daniil Orel, Rituraj Joshi, Maiya Goloburda, Yuxia Wang · Feb 19, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- LaVCa: LLM-assisted Visual Cortex Captioning
Takuya Matsuyama, Shinji Nishimoto, Yu Takagi · Feb 19, 2025 · Citations: 0
- Don't Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints
Nicolò Penzo, Marco Guerini, Bruno Lepri, Goran Glavaš, Sara Tonelli · Feb 19, 2025 · Citations: 0
Finally, we assess the level of obtained WMPCs via human and LLM-as-a-judge evaluations.
- MKE-Coder: Multi-Axial Knowledge with Evidence Verification in ICD Coding for Chinese EMRs
Xinxin You, Xien Liu, Xue Yang, Ziyi Wang, Ji Wu · Feb 19, 2025 · Citations: 0
In the practical evaluation of our method within simulated real coding scenarios, it has been demonstrated that our approach significantly aids coders in enhancing both their coding accuracy and speed.
- Reflection of Episodes: Learning to Play Game from Expert and Self Experiences
Xiaojie Xu, Zongyuan Li, Chang Lu, Runnan Qi, Yanan Ni · Feb 19, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Cyber-Physical Systems Security: A Comprehensive Review of Anomaly Detection Techniques
Danial Abshari, Meera Sridhar · Feb 18, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- 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 · Citations: 0
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…
- Conditioning LLMs to Generate Code-Switched Text
Maite Heredia, Gorka Labaka, Jeremy Barnes, Aitor Soroa · Feb 18, 2025 · Citations: 0
Pairwise Preference
Code-switching (CS) is still a critical challenge in Natural Language Processing (NLP), due to the limited availability of large-scale, diverse CS datasets for robust training and evaluation.
- Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models
Neeraj Gangwar, Suma P Bhat, Nickvash Kani · Feb 18, 2025 · Citations: 0
Our experiments on multiple reasoning benchmarks demonstrate that incorporating an arithmetic dataset, whether through targeted fine-tuning or within an instruction-tuning mixture, enhances models' arithmetic capabilities, thereby improving…
- Using the Path of Least Resistance to Explain Deep Networks
Sina Salek, Joseph Enguehard · Feb 17, 2025 · Citations: 0
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 · Citations: 0
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…
- Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
Haoyu Lei, Kaiwen Zhou, Yinchuan Li, Zhitang Chen, Farzan Farnia · Feb 15, 2025 · Citations: 0
- Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
Bettina Messmer, Vinko Sabolčec, Martin Jaggi · Feb 14, 2025 · Citations: 0
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…
- Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
Shruti Joshi, Andrea Dittadi, Sébastien Lachapelle, Dhanya Sridhar · Feb 14, 2025 · Citations: 0
- EmbBERT: Attention Under 2 MB Memory
Riccardo Bravin, Massimo Pavan, Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri · Feb 14, 2025 · Citations: 0
Extensive experiments on the curated TinyNLP benchmark and the GLUE suite confirm that EmbBERT achieves competitive accuracy, comparable to that of larger SotA models, and consistently outperforms downsized versions of BERT and MAMBA of…
- Enhanced Structured Lasso Pruning with Class-wise Information
Xiang Liu, Mingchen Li, Xia Li, Leigang Qu, Guansu Wang · Feb 13, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
Cheng Fang, Rishabh Dixit, Waheed U. Bajwa, Mert Gurbuzbalaban · Feb 11, 2025 · Citations: 0
- Hallucination, Monofacts, and Miscalibration: An Empirical Investigation
Miranda Muqing Miao, Michael Kearns · Feb 11, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Streaming Attention Approximation via Discrepancy Theory
Ekaterina Kochetkova, Kshiteej Sheth, Insu Han, Amir Zandieh, Michael Kapralov · Feb 11, 2025 · Citations: 0
- Lexical categories of stem-forming roots in Mapudüngun verb forms
Andrés Chandía · Feb 11, 2025 · Citations: 0
Critique Edit
After developing a computational system for morphological analysis of the Mapuche language, and evaluating it with texts from various authors and styles, it became necessary to verify the linguistic assumptions of the source used as the…
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
Xialie Zhuang, Zhikai Jia, Jianjin Li, Zhenyu Zhang, Li Shen · Feb 11, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Byte-token Enhanced Language Models for Temporal Point Processes Analysis
Quyu Kong, Yixuan Zhang, Yang Liu, Panrong Tong, Enqi Liu · Feb 11, 2025 · Citations: 0
This approach allows Language-TPP to achieve state-of-the-art performance across multiple TPP benchmarks, including event time prediction and type prediction, on real-world Web datasets spanning e-commerce reviews, social media and online…
- Post-detection inference for sequential changepoint localization
Aytijhya Saha, Aaditya Ramdas · Feb 10, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- 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 · Citations: 0
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.
- A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models
Huiyao Chen, Meishan Zhang, Jing Li, Lilja Øvrelid, Jan Hajič · Feb 9, 2025 · Citations: 0
We extend the scope of SRL surveys to cover multimodal settings including visual, video, and speech modalities, and analyze structural differences in evaluation across these modalities.
- Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
Manh Luong, Khai Nguyen, Dinh Phung, Gholamreza Haffari, Lizhen Qu · Feb 8, 2025 · Citations: 0
Our kernel also improves the reasoning accuracy of the MMAU-test-mini benchmarks by 4\%.
- Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data
Haoyan Yang, Khiem Le, Ting Hua, Shangqian Gao, Binfeng Xu · Feb 8, 2025 · Citations: 0
Pairwise Preference
To overcome these challenges, we introduce Dynamic Noise Preference Optimization (DNPO), which combines dynamic sample labeling for constructing preference pairs with controlled, trainable noise injection during preference optimization.
- Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Jonathan Laurent, André Platzer · Feb 7, 2025 · Citations: 0
Demonstrations Web Browsing
We propose oracular programming: a foundational paradigm for integrating traditional, explicit computations with inductive oracles such as LLMs.
- From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement
Jiamin Xu, Ivan Nazarov, Aditya Rastogi, África Periáñez, Kyra Gan · Feb 7, 2025 · Citations: 0
This paper addresses the poor finite-horizon performance of existing online restless bandit (RB) algorithms, which stems from the prohibitive sample complexity of learning a full Markov decision process (MDP) for each agent.
- Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
Thierry Bossy, Julien Vignoud, Tahseen Rabbani, Juan R. Troncoso Pastoriza, Martin Jaggi · Feb 7, 2025 · Citations: 0
- HOG-Diff: Higher-Order Guided Diffusion for Graph Generation
Yiming Huang, Tolga Birdal · Feb 6, 2025 · Citations: 0
Pairwise Preference
Extensive experiments across eight graph generation benchmarks, spanning diverse domains and including large-scale settings, demonstrate the scalability of our method and its superior performance on both pairwise and higher-order…
- Physics-Informed Evolution: An Evolutionary Framework for Solving Quantum Control Problems Involving the Schrödinger Equation
Kaichen Ouyang, Mingyang Yu, Zong Ke, Jun Zhang, Yi Chen · Feb 6, 2025 · Citations: 0
We validate PIE on three representative quantum control benchmarks: state preparation in V-type three-level systems, entangled state generation in superconducting quantum circuits, and two-atom cavity QED systems.
- vCache: Verified Semantic Prompt Caching
Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron, Kyle Chu, Shu Liu · Feb 6, 2025 · Citations: 0
We release the vCache implementation and four benchmarks to support future research.
- AStar: Boosting Multimodal Reasoning with Automated Structured Thinking
Jinyang Wu, Mingkuan Feng, Guocheng Zhai, Shuai Zhang, Zheng Lian · Feb 4, 2025 · Citations: 0