- Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Chungpa Lee, Jy-yong Sohn, Kangwook Lee · Feb 26, 2026 · Citations: 0
Demonstrations Automatic Metrics
Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations.
- AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
Abhay Sheshadri, Aidan Ewart, Kai Fronsdal, Isha Gupta, Samuel R. Bowman · Feb 26, 2026 · Citations: 0
Demonstrations Automatic Metrics
We introduce AuditBench, an alignment auditing benchmark.
- FewMMBench: A Benchmark for Multimodal Few-Shot Learning
Mustafa Dogan, Ilker Kesen, Iacer Calixto, Aykut Erdem, Erkut Erdem · Feb 25, 2026 · Citations: 0
Demonstrations Automatic Metrics
In this paper, we introduce FewMMBench, a comprehensive benchmark designed to evaluate MLLMs under few-shot conditions, with a focus on In-Context Learning (ICL) and Chain-of-Thought (CoT) prompting.
- Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen · Feb 25, 2026 · Citations: 0
Demonstrations Automatic Metrics
Extensive experiments on five KGQA benchmark datasets demonstrate that, to the best of our knowledge, our method achieves state-of-the-art performance, outperforming not only open-source but also even closed-source LLMs.
- Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar, Zihan Guan, Sheng Li · Feb 24, 2026 · Citations: 0
Pairwise PreferenceRed Team Automatic Metrics
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs).
- A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications
Shruti Srivastava, Kiranmayee Janardhan, Shaurya Jauhari · Feb 24, 2026 · Citations: 0
Red Team Automatic Metrics
These limitations have driven the evolution toward auto-mated red teaming, which leverages artificial intelligence and automation to deliver efficient and adaptive security evaluations.
- SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
Yifei Xu, Guilherme Potje, Shivam Shandilya, Tiancheng Yuan, Leonardo de Oliveira Nunes · Feb 24, 2026 · Citations: 0
Rubric RatingRed Team Automatic Metrics
Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training.
- Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
Rakshit Trivedi, Kartik Sharma, David C Parkes · Feb 24, 2026 · Citations: 0
Demonstrations Automatic Metrics Multi Agent
Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts.
- Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore · Feb 23, 2026 · Citations: 0
Red Team Simulation Env
Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue.
- MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav, Ava Cai, Kevin Zhu · Feb 21, 2026 · Citations: 0
Red Team Automatic Metrics
Defending LLMs against adversarial jailbreak attacks remains an open challenge.
- FENCE: A Financial and Multimodal Jailbreak Detection Dataset
Mirae Kim, Seonghun Jeong, Youngjun Kwak · Feb 20, 2026 · Citations: 0
Red Team Automatic Metrics
A baseline detector trained on FENCE achieves 99 percent in-distribution accuracy and maintains strong performance on external benchmarks, underscoring the dataset's robustness for training reliable detection models.
- From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences
Yi-Chih Huang · Feb 19, 2026 · Citations: 0
Demonstrations Automatic Metrics
Generative AI is reshaping knowledge work, yet existing research focuses predominantly on software engineering and the natural sciences, with limited methodological exploration for the humanities and social sciences.
- IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages
Priyaranjan Pattnayak, Sanchari Chowdhuri · Feb 18, 2026 · Citations: 0
Red Team Automatic Metrics
Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied.
- Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut · Feb 18, 2026 · Citations: 0
Red Team Automatic Metrics
LLM-based agents execute real-world workflows via tools and memory.
- Intent Laundering: AI Safety Datasets Are Not What They Seem
Shahriar Golchin, Marc Wetter · Feb 17, 2026 · Citations: 0
Red Team Automatic Metrics
We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice.
- Perspectives - Interactive Document Clustering in the Discourse Analysis Tool Suite
Tim Fischer, Chris Biemann · Feb 17, 2026 · Citations: 0
Demonstrations Automatic Metrics
This paper introduces Perspectives, an interactive extension of the Discourse Analysis Tool Suite designed to empower Digital Humanities (DH) scholars to explore and organize large, unstructured document collections.
- Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework
Mengze Hong, Chen Jason Zhang, Zichang Guo, Hanlin Gu, Di Jiang · Feb 17, 2026 · Citations: 0
Demonstrations Automatic Metrics
Existing approaches either rely on modular system designs with extensive agent orchestration or employ over-simplified instruction schemas, providing limited guidance and poor generalizability.
- Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Lukas Struppek, Adam Gleave, Kellin Pelrine · Feb 16, 2026 · Citations: 0
Red Team Automatic Metrics
As the capabilities of large language models continue to advance, so does their potential for misuse.
- Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis · Feb 12, 2026 · Citations: 0
Red Team Automatic Metrics
Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems.
- What Matters For Safety Alignment?
Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong · Jan 7, 2026 · Citations: 0
Red Team Automatic Metrics Tool Use
This paper presents a comprehensive empirical study on the safety alignment capabilities.
- Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Iker García-Ferrero, David Montero, Roman Orus · Dec 18, 2025 · Citations: 0
Red Team Automatic Metrics
We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction.
- AITutor-EvalKit: Exploring the Capabilities of AI Tutors
Numaan Naeem, Kaushal Kumar Maurya, Kseniia Petukhova, Ekaterina Kochmar · Dec 3, 2025 · Citations: 0
Demonstrations Automatic Metrics
We present AITutor-EvalKit, an application that uses language technology to evaluate the pedagogical quality of AI tutors, provides software for demonstration and evaluation, as well as model inspection and data visualization.
- Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar · Oct 30, 2025 · Citations: 0
Red Team Automatic Metrics
Our finetuned models achieve consistent improvements on instruction following and instruction hierarchy benchmarks, achieving roughly a 20% improvement on the IHEval conflict setup.
- Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han · Oct 29, 2025 · Citations: 0
Demonstrations Automatic Metrics Long Horizon
Beyond reasoning benchmarks, SRL generalizes effectively to agentic software engineering tasks, establishing it as a robust and versatile training framework for reasoning-oriented LLMs.
- MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation
Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang · Oct 21, 2025 · Citations: 0
Demonstrations Simulation Env Long Horizon
Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming.
- SPACeR: Self-Play Anchoring with Centralized Reference Models
Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka · Oct 20, 2025 · Citations: 0
Demonstrations Simulation Env Multi Agent
Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable.
- Mapping Semantic & Syntactic Relationships with Geometric Rotation
Michael Freenor, Lauren Alvarez · Oct 10, 2025 · Citations: 0
Demonstrations Automatic Metrics
Understanding how language and embedding models encode semantic relationships is fundamental to model interpretability.
- A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Xuan Luo, Yue Wang, Zefeng He, Geng Tu, Jing Li · Sep 17, 2025 · Citations: 0
Red Team Automatic Metrics
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses.
- Role-Aware Language Models for Secure and Contextualized Access Control in Organizations
Saeed Almheiri, Yerulan Kongrat, Adrian Santosh, Ruslan Tasmukhanov, Josemaria Loza Vera · Jul 31, 2025 · Citations: 0
Red Team Automatic Metrics
Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints.
- Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaschel · Jun 23, 2025 · Citations: 0
Demonstrations Automatic Metrics
Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important implica
- When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
Yuxin Xiao, Sana Tonekaboni, Walter Gerych, Vinith Suriyakumar, Marzyeh Ghassemi · Jun 9, 2025 · Citations: 0
Red Team Automatic Metrics
In this work, we seek to understand whether style patterns compromise LLM safety, how superficial style alignment increases model vulnerability, and how best to mitigate these risks during alignment.
- RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Zeyi Liao, Jaylen Jones, Linxi Jiang, Yuting Ning, Eric Fosler-Lussier · May 28, 2025 · Citations: 0
Red Team Simulation Env Web Browsing
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection.
- Refusal Direction is Universal Across Safety-Aligned Languages
Xinpeng Wang, Mingyang Wang, Yihong Liu, Hinrich Schütze, Barbara Plank · May 22, 2025 · Citations: 0
Red Team Automatic Metrics
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety.
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao · Apr 7, 2025 · Citations: 0
Red Team Automatic Metrics
We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-cont
- Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu · Feb 28, 2025 · Citations: 0
Red Team Automatic Metrics
To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues.
- Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Jonathan Laurent, André Platzer · Feb 7, 2025 · Citations: 0
Demonstrations Automatic Metrics 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
