- Moral Preferences of LLMs Under Directed Contextual Influence
Phil Blandfort, Tushar Karayil, Urja Pawar, Robert Graham, Alex McKenzie · Feb 26, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Moral benchmarks for LLMs typically use context-free prompts, implicitly assuming stable preferences.
- ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li · Feb 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Analysis shows that, by enabling on-policy thinking language selection as an action during RL, ExpLang effectively extends the RL exploration space with diversified language preference and improves the RL exploitation outcome with leveraged
- DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs
Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu · Feb 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
This ``one-size-fits-all'' strategy often neglects model-specific and task-specific preferences, resulting in inaccurate or over-lengthy responses to graph-related queries.
- The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems
Hyo Jin Kim · Feb 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Although initially formulated for human truth-telling under asymmetric stakes, the same phase-dynamic architecture extends to AI systems operating under policy constraints and alignment filters.
- CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
Zhijiang Tang, Linhua Wang, Jiaxin Qi, Weihao Jiang, Peng Hou · Feb 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.
- Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
Sweta Karlekar, Carolina Zheng, Magnus Saebo, Nicolas Beltran-Velez, Shuyang Yu · Feb 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Building on this observation, we introduce Duel-Evolve, an evolutionary optimization algorithm that replaces external scalar rewards with pairwise preferences elicited from the same LLM used to generate candidates.
- 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).
- Probing Graph Neural Network Activation Patterns Through Graph Topology
Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis · Feb 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs.
- HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao · Feb 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints.
- 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.
- Balancing Multiple Objectives in Urban Traffic Control with Reinforcement Learning from AI Feedback
Chenyang Zhao, Vinny Cahill, Ivana Dusparic · Feb 24, 2026 · Citations: 0
Pairwise PreferenceRlaif Or Synthetic Feedback Human Eval
Preference-based RL offers an appealing alternative by learning from human preferences over pairs of behavioural outcomes.
- CAMEL: Confidence-Gated Reflection for Reward Modeling
Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar · Feb 24, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics
Reward models play a fundamental role in aligning large language models with human preferences.
- gencat: Generative computerized adaptive testing
Wanyong Feng, Andrew Lan · Feb 23, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We train the model in a two-step process, first via Supervised Fine-Tuning and then via preference optimization for knowledge-response alignment.
- 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.
- Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
Maryam Amirizaniani, Alireza Salemi, Hamed Zamani · Feb 22, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context.
- Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language
Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov · Feb 21, 2026 · Citations: 0
Pairwise Preference Human Eval
One annotator pair achieved almost perfect agreement ($κ= 0.8743$; $93.8\%$ raw agreement), exceeding a number of reported benchmarks for English sarcasm research works.
- Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models
Abraham Paul Elenjical, Vivek Hruday Kavuri, Vasudeva Varma · Feb 21, 2026 · Citations: 0
Pairwise Preference Human Eval
We introduce a psychologically grounded metacognitive framework that operationalizes Ann Brown's regulatory cycle (Planning, Monitoring, and Evaluation) as a structured prompting architecture, and study its integration within a lightweight
- 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.
- Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications
Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar · Feb 20, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed.
- Validating Political Position Predictions of Arguments
Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn · Feb 20, 2026 · Citations: 0
Pairwise Preference Human Eval
Real-world knowledge representation often requires capturing subjective, continuous attributes -- such as political positions -- that conflict with pairwise validation, the widely accepted gold standard for human evaluation.
- Simplifying Outcomes of Language Model Component Analyses with ELIA
Aaron Louis Eidt, Nils Feldhus · Feb 20, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
The effectiveness of this approach was empirically validated through a mixed-methods user study, which revealed a clear preference for interactive, explorable interfaces over simpler, static visualizations.
- 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.
- Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking
Iskar Deng, Nathalia Xu, Shane Steinert-Threlkeld · Feb 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order.
- Modeling Distinct Human Interaction in Web Agents
Faria Huq, Zora Zhiruo Wang, Zhanqiu Guo, Venu Arvind Arangarajan, Tianyue Ou · Feb 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Web Browsing
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold.
- Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
Serin Kim, Sangam Lee, Dongha Lee · Feb 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Large language models have advanced web agents, yet current agents lack personalization capabilities.
- 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.
- Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
Yuyan Bu, Xiaohao Liu, ZhaoXing Ren, Yaodong Yang, Juntao Dai · Feb 18, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment.
- Who can we trust? LLM-as-a-jury for Comparative Assessment
Mengjie Qian, Guangzhi Sun, Mark J. F. Gales, Kate M. Knill · Feb 18, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements.
- 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.
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen · Feb 18, 2026 · Citations: 0
Pairwise Preference Simulation Env Web Browsing
Existing evaluations of agents with memory typically assess memorization and action in isolation.
- Learning Personalized Agents from Human Feedback
Kaiqu Liang, Julia Kruk, Shengyi Qian, Xianjun Yang, Shengjie Bi · Feb 18, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users.
- Multi-Objective Alignment of Language Models for Personalized Psychotherapy
Mehrab Beikzadeh, Yasaman Asadollah Salmanpour, Ashima Suvarna, Sriram Sankararaman, Matteo Malgaroli · Feb 17, 2026 · Citations: 0
Pairwise PreferenceExpert Verification Automatic Metrics
While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to balance patient preferences with clinical safety.
- 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.
- ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models
Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Rosé · Feb 17, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In practice, users iteratively refine visualizations through multi-turn interactions that require maintaining common ground, tracking prior edits, and adapting to evolving preferences.
- Rethinking Metrics for Lexical Semantic Change Detection
Roksana Goworek, Haim Dubossarsky · Feb 17, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Lexical semantic change detection (LSCD) increasingly relies on contextualised language model embeddings, yet most approaches still quantify change using a small set of semantic change metrics, primarily Average Pairwise Distance (APD) and
- In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
Mohammad Aflah Khan, Mahsa Amani, Soumi Das, Bishwamittra Ghosh, Qinyuan Wu · Feb 17, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms.
- The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Xiaoze Liu, Ruowang Zhang, Weichen Yu, Siheng Xiong, Liu He · Feb 17, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Multi Agent
Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain shackled by the inefficiency of discrete text communication, which imposes significant runtime overhead and informati
- How to Train Your Long-Context Visual Document Model
Austin Veselka · Feb 16, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We systematically study continued pretraining, supervised finetuning, and preference optimization for 24B and 32B parameter models, backed by extensive LC evaluations and ablations to bridge this gap, and achieve state-of-the-art performanc
- Cold-Start Personalization via Training-Free Priors from Structured World Models
Avinandan Bose, Shuyue Stella Li, Faeze Brahman, Pang Wei Koh, Simon Shaolei Du · Feb 16, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available.
- Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation
Shiwei Hong, Lingyao Li, Ethan Z. Rong, Chenxinran Shen, Zhicong Lu · Feb 16, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Human Eval Multi Agent
Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined.
- 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.
- Investigation for Relative Voice Impression Estimation
Kenichi Fujita, Yusuke Ijima · Feb 15, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
The estimation target is a low-dimensional vector derived from subjective evaluations, quantifying the perceptual shift of the second utterance relative to the first along an antonymic axis (e.g., ``Dark--Bright'').
- SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Sher Badshah, Ali Emami, Hassan Sajjad · Feb 13, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Large language models (LLMs) are increasingly used as judges to replace costly human preference labels in pairwise evaluation.
- 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.
- Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao · Feb 11, 2026 · Citations: 0
Pairwise Preference Simulation Env Tool Use
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.
- The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage
Preni Golazizian, Elnaz Rahmati, Jackson Trager, Zhivar Sourati, Nona Ghazizadeh · Feb 10, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Human Eval
To this end, we (i) develop a domain-specific evaluation rubric grounded in procedural justice theory, LAPD training materials, and extensive fieldwork; (ii) introduce a rubric-driven preference data construction framework for perspective-c
- Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
Jingyi Xu, Xingyu Ren, Zhoupeng Shou, Yumeng Zhang, Zhiqiang You · Jan 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success.
- RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind
Zhitao He, Zongwei Lyu, Yi R Fung · Jan 22, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Human Eval
In this paper, we introduce RebuttalAgent, the first framework to ground academic rebuttal in Theory of Mind (ToM), operationalized through a ToM-Strategy-Response (TSR) framework that models reviewer mental state, formulates persuasion str
- Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz · Jan 14, 2026 · Citations: 0
Pairwise Preference Simulation Env Long Horizon
Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodie
- A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding
Dilara Torunoğlu-Selamet, Dogukan Arslan, Rodrigo Wilkens, Wei He, Doruk Eryiğit · Jan 13, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
The dataset, containing 34 languages and over ten thousand items, allows comparative analyses of idiomatic patterns among language-specific realisations and preferences in order to gather insights about shared cultural aspects.
- Reward Modeling from Natural Language Human Feedback
Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu, Pinyi Zhang · Jan 12, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics
Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs).
- HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue
Laya Iyer, Kriti Aggarwal, Sanmi Koyejo, Gail Heyman, Desmond C. Ong · Jan 9, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Human EvalLlm As Judge
Despite rapid progress in language models, we still lack a clear way to understand how their abilities in these interpersonal domains compare to those of humans.
- 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.
- ARGUS: Adaptive Rotation-Invariant Geometric Unsupervised System
Anantha Sharma · Jan 3, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Detecting distributional drift in high-dimensional data streams presents fundamental challenges: global comparison methods scale poorly, projection-based approaches lose geometric structure, and re-clustering methods suffer from identity in
- 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.
- Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution
Jonathan Kamp, Roos Bakker, Dominique Blok · Dec 11, 2025 · Citations: 0
Pairwise Preference Automatic Metrics
In this work, we delve beyond the superficial inconsistencies between attribution methods, structuring their biases through a model- and method-agnostic framework of three evaluation metrics.
- Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu · Nov 7, 2025 · Citations: 0
Pairwise Preference Automatic Metrics
We introduce a framework able to synthesize vision-centric problems spanning diverse levels of complexity, and the resulting dataset with over 1M high-quality problems including: reasoning traces, preference data, and instruction prompts su
- BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
Qiusi Zhan, Hyeonjeong Ha, Rui Yang, Sirui Xu, Hanyang Chen · Oct 31, 2025 · Citations: 0
Pairwise Preference Automatic MetricsSimulation Env Long Horizon
Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs.
- 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.
