- Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou · Apr 8, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Human EvalAutomatic Metrics
Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
- Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study
Yosuke Yamagishi, Atsushi Takamatsu, Yasunori Hamaguchi, Tomohiro Kikuchi, Shouhei Hanaoka · Apr 2, 2026 · Citations: 0
Pairwise Preference Llm As JudgeAutomatic Metrics
A board-certified radiologist and a radiology resident independently performed blinded pairwise evaluations across 4 criteria: terminology accuracy, readability, overall quality, and radiologist-style authenticity.
- VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents
Yuhao Chen, Yi Xu, Xinyun Ding, Xiang Fang, Shuochen Liu · Mar 25, 2026 · Citations: 0
Pairwise Preference Simulation Env Tool Use
With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions.
- Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
José Pombal, Ricardo Rei, André F. T. Martins · Apr 8, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Llm As Judge
We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings.
- From Consensus to Split Decisions: ABC-Stratified Sentiment in Holocaust Oral Histories
Daban Q. Jaff · Mar 30, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
After assembling model outputs, we introduce an agreement-based stability taxonomy (ABC) to stratify inter-model output stability.
- Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation
Richard J. Young · Mar 20, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Three classifiers (a regex-only detector, a regex-plus-LLM pipeline, and a Claude Sonnet 4 judge) are applied to 10,276 influenced reasoning traces from 12 open-weight models spanning 9 families and 7B to 1T parameters.
- HyperMem: Hypergraph Memory for Long-Term Conversations
Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang · Apr 9, 2026 · Citations: 0
Pairwise Preference Llm As JudgeAutomatic Metrics
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues.
- Signals: Trajectory Sampling and Triage for Agentic Interactions
Shuguang Chen, Adil Hafeez, Salman Paracha · Apr 1, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
We propose a lightweight, signal-based framework for triaging agentic interaction trajectories.
- Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
Davide Di Gioia · Mar 23, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
Autonomous agents operating in continuous environments must decide not only what to do, but when to act.
- Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan · Mar 16, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
To address these challenges, we introduce SDiaReward, an end-to-end multi-turn reward model trained on SDiaReward-Dataset, a novel collection of episode-level preference pairs explicitly targeting these gaps.
- Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE
Hejin Huang, Jusheng Zhang, Kaitong Cai, Jian Wang, Rong Pan · Mar 31, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems.
- Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang · Apr 1, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We study whether phone-use agents respect privacy while completing benign mobile tasks.
- ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims
Raia Abu Ahmad, Max Upravitelev, Aida Usmanova, Veronika Solopova, Georg Rehm · Mar 27, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In addition to standard evaluation metrics (Recall@K and Binary Preference), we adapt an automated framework to assess retrieval quality under incomplete annotations, exposing systematic biases in how conventional metrics rank systems.
- Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment
Xinyu Zhang · Mar 23, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We further demonstrate that constructing DPO preference pairs from NSRSA verification teaches the model to distinguish sound from flawed reasoning (reward accuracy 46% to 63%).
- DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith · Mar 23, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility.
- CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
Hao Wang, Licheng Pan, Zhichao Chen, Chunyuan Zheng, Zhixuan Chu · Mar 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on experimental feedback data collected from human annotators under controlled and costly…
- TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning
Dilina Rajapakse, Juan C. Rosero, Ivana Dusparic · Mar 23, 2026 · Citations: 0
Pairwise Preference Long Horizon
Multi-Objective Reinforcement Learning (MORL) addresses this limitation by enabling agents to optimize several objectives simultaneously, explicitly reasoning about trade-offs between them.
- DongYuan: An LLM-Based Framework for Integrative Chinese and Western Medicine Spleen-Stomach Disorders Diagnosis
Hua Li, Yingying Li, Xiaobin Feng, Xinyi Fu, Lifeng Dong · Mar 30, 2026 · Citations: 0
Pairwise Preference Web Browsing
While large language models (LLMs) offer new potential for medical applications, they face three major challenges in the context of integrative Chinese and Western medicine (ICWM): a lack of high-quality data, the absence of models capable…
- MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang · Apr 7, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.
- Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Yuhang Wu, Xiangqing Shen, Fanfan Wang, Cangqi Zhou, Zhen Wu · Apr 2, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.
- Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences
Simona-Vasilica Oprea, Adela Bâra · Apr 1, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Using the Anthropic HHRLHF dataset, we evaluate ten diverse large language models LLMs under a standard pairwise preference setting, where baseline performance remains below 0.74 ROC AUC, highlighting the difficulty of the task.
- MemRerank: Preference Memory for Personalized Product Reranking
Zhiyuan Peng, Xuyang Wu, Huaixiao Tou, Yi Fang, Yu Gong · Mar 31, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch.
- Routing Sensitivity Without Controllability: A Diagnostic Study of Fairness in MoE Language Models
Junhyeok Lee, Kyu Sung Choi · Mar 28, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
FARE reveals that routing-level preference shifts are either unachievable (Mixtral, Qwen1.5, Qwen3), statistically non-robust (DeepSeekMoE), or accompanied by substantial utility cost (OLMoE, -4.4%p CrowS-Pairs at -6.3%p TQA).
- Towards Reward Modeling for AI Tutors in Math Mistake Remediation
Kseniia Petukhova, Ekaterina Kochmar · Mar 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We develop and release Bradley-Terry preference models trained on weighted-sum rankings that we automatically create from MRBench, synthetic pairs, and data combinations.
- Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning
He Huang · Mar 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We evaluate alignment quality using pairwise metrics, specifically ROC-AUC and triplet accuracy, on curated Egyptian-English and intra-Egyptian cognate datasets.
- A Comparative Empirical Study of Catastrophic Forgetting Mitigation in Sequential Task Adaptation for Continual Natural Language Processing Systems
Aram Abrahamyan, Sachin Kumar · Mar 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Performance is assessed with average accuracy, macro F1, and backward transfer, capturing the stability-plasticity trade-off across the task sequence.
- Self-Debias: Self-correcting for Debiasing Large Language Models
Xuan Feng, Shuai Zhao, Luwei Xiao, Tianlong Gu, Bo An · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints.
- Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
Shiwan Zhao, Zhihu Wang, Xuyang Zhao, Jiaming Zhou, Caiyue Xu · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines.
- AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
Tianyi Li, Zixuan Wang, Guidong Lei, Xiaodong Li, Hui Li · Mar 23, 2026 · Citations: 0
Pairwise Preference Tool Use
To address this, we present AgenticRec, a ranking-oriented agentic recommendation framework that optimizes the entire decision-making trajectory (including intermediate reasoning, tool invocation, and final ranking list generation) under…
- HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
Zhicong Lu, Zichuan Lin, Wei Jia, Changyuan Tian, Deheng Ye · Mar 19, 2026 · Citations: 0
Pairwise Preference Long Horizon
While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited.
- How Large Language Models Balance Internal Knowledge with User and Document Assertions
Shuowei Li, Haoxin Li, Wenda Chu, Yi Fang · Apr 24, 2026 · Citations: 0
Pairwise Preference Simulation Env
A model's ability to reliably process these sources is key to system safety.
- Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
Xin Sun, Di Wu, Sijing Qin, Isao Echizen, Abdallah El Ali · Apr 7, 2026 · Citations: 0
Pairwise Preference Llm As Judge
Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge).
- Text-to-Stage: Spatial Layouts from Long-form Narratives
Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse, Sanjeel Parekh, Calvin Murdock · Mar 18, 2026 · Citations: 0
Pairwise Preference Llm As Judge
In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications.
- PrefPO: Pairwise Preference Prompt Optimization
Rahul Singhal, Pradyumna Tambwekar, Karime Maamari · Mar 13, 2026 · Citations: 0
Pairwise Preference
We introduce PrefPO, a minimal prompt optimization approach inspired by reinforcement learning from human feedback (RLHF).
- JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
Aichen Cai, Anmeng Zhang, Anyu Li, Bo Zhang, Bohua Cai · Apr 3, 2026 · Citations: 0
Pairwise Preference
JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale…
- FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
Taejin Jeong, Joohyeok Kim, Jinyeong Kim, Chanyoung Kim, Seong Jae Hwang · Mar 26, 2026 · Citations: 0
Pairwise Preference
To address this, we propose FEAST (Fully connected Expressive Attention for Spatial Transcriptomics), an attention-based framework that models the tissue as a fully connected graph, enabling the consideration of all pairwise interactions.
- Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Weixu Zhang, Ye Yuan, Changjiang Han, Yuxing Tian, Zipeng Sun · Apr 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In this work, we adopt a mechanistic interpretability perspective and hypothesize the existence of a sparse set of Preference Heads, attention heads that encode user specific stylistic and topical preferences and exert a causal influence on…
- Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
Chaoran Chen, Dayu Yuan, Peter Kairouz · Apr 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In agentic workflows, LLMs frequently process retrieved contexts that are legally protected from further training.
- TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Weian Mao, Xi Lin, Wei Huang, Yuxin Xie, Tianfu Fu · Apr 6, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Via the trigonometric series, we use the distance preference characterized by these centers to score keys according to their positions, and also leverage Q/K norms as an additional signal for importance estimation.
- PLOT: Enhancing Preference Learning via Optimal Transport
Liang Zhu, Yuelin Bai, Xiankun Ren, Jiaxi Yang, Lei Zhang · Apr 2, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Preference learning in Large Language Models (LLMs) has advanced significantly, yet existing methods remain limited by modest performance gains, high computational costs, hyperparameter sensitivity, and insufficient modeling of global…
- ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models
Delip Rao, Feijiang Han, Chris Callison-Burch · Apr 2, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
By contrast, zero-shot chain-of-thought on the base Gemma3-1B harms accuracy relative to direct answers, and preference optimization with a simple format+accuracy reward underperforms supervised reasoning.
- OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
Ben Chen, Siyuan Wang, Yufei Ma, Zihan Liang, Xuxin Zhang · Mar 25, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement.
- BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents
Praveen Kumar Myakala, Manan Agrawal, Rahul Manche · Mar 25, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics
LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved.
- IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge
Ali Abdelaal, Mohammed Nader Al Haffar, Mahmoud Fawzi, Walid Magdy · Mar 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We introduce IslamicMMLU, a benchmark of 10,013 multiple-choice questions spanning three tracks: Quran (2,013 questions), Hadith (4,000 questions), and Fiqh (jurisprudence, 4,000 questions).
- Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
Yanbei Jiang, Amr Keleg, Ryandito Diandaru, Jey Han Lau, Lea Frermann · Apr 7, 2026 · Citations: 0
Pairwise Preference
Our empirical analysis reveals that off-the-shelf LLMs and standard alignment techniques, including prompt engineering and Direct Preference Optimization, fail to reliably control output distributions.
- TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
Xinliang Frederick Zhang, Lu Wang · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences.
- TARo: Token-level Adaptive Routing for LLM Test-time Alignment
Arushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang, Dipesh Tamboli · Mar 19, 2026 · Citations: 0
Pairwise Preference
Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly for preference alignment rather than reasoning.
- Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination
Cem Uluoglakci, Tugba Taskaya Temizel · Mar 18, 2026 · Citations: 0
Pairwise Preference
We also release HypoTermQA-Enhanced, a benchmark for hallucination tendency strengthened through multiple validations.
- Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
Zhiyu Cao, Peifeng Li, Qiaoming Zhu · Apr 8, 2026 · Citations: 0
Pairwise Preference
Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation.
- From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs
Xiaoyong Guo, Nanjie Li, Zijie Zeng, Kai Wang, Hao Huang · Mar 25, 2026 · Citations: 0
Pairwise Preference
We propose a unified training framework to improve robustness under realistic histories: (i) Teacher Error Knowledge by using Whisper large-v3 hypotheses as training-time history, (ii) Context Dropout to regularize over-reliance on history,…
- Evaluating Learner Representations for Differentiation Prior to Instructional Outcomes
Junsoo Park, Youssef Medhat, Htet Phyo Wai, Ploy Thajchayapong, Ashok K. Goel · Apr 7, 2026 · Citations: 0
Pairwise Preference
We introduce distinctiveness, a representation-level measure that evaluates how each learner differs from others in the cohort using pairwise distances, without requiring clustering, labels, or task-specific evaluation.
- Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once
Harnoor Dhingra · Apr 2, 2026 · Citations: 0
Pairwise Preference
We organize tasks into four normative contexts: epistemic (factuality), interactional (user utility), societal (representation), and safety (robustness).
- Convergent Representations of Linguistic Constructions in Human and Artificial Neural Systems
Pegah Ramezani, Thomas Kinfe, Andreas Maier, Achim Schilling, Patrick Krauss · Mar 31, 2026 · Citations: 0
Pairwise Preference
The present study tests these predictions in human neural activity using electroencephalography (EEG).
- MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
Kexin Huang, Liwei Fan, Botian Jiang, Yaozhou Jiang, Qian Tu · Mar 30, 2026 · Citations: 0
Pairwise Preference
Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models.
- Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu · Mar 25, 2026 · Citations: 0
Pairwise PreferenceRubric Rating
We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and models weigh…
- Agentic Personas for Adaptive Scientific Explanations with Knowledge Graphs
Susana Nunes, Tiago Guerreiro, Catia Pesquita · Mar 23, 2026 · Citations: 0
Pairwise Preference
However, the scarcity of human experts limits the use of direct human feedback to produce adaptive explanations.
- When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
Yubo Li, Ramayya Krishnan, Rema Padman · Mar 23, 2026 · Citations: 0
Pairwise Preference
Applied to 102 handbooks from 23 centers and 1,115 benchmark questions, the framework quantifies heterogeneity across four dimensions: question, topic, organ, and center.
- From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation
Pujun Zheng, Jiacheng Yao, Jinquan Zheng, Chenyang Gu, Guoxiu He · Mar 18, 2026 · Citations: 0
Pairwise Preference
Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently.
- Beyond bouba/kiki: Multidimensional semantic signals are deeply woven into the fabric of natural language
Gexin Zhao · Mar 18, 2026 · Citations: 0
Pairwise Preference
Here we show that individual letter-phonemes in English carry structured, multidimensional semantic signals.
- Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
William Peng, Josheev Rai, Kevin Tseng, Siwei Wang, Sean Wu · Mar 16, 2026 · Citations: 0
Pairwise Preference
We present the first open-source mHC language model (https://huggingface.co/wgpeng/mhc-780m) and analyze the multiple-stream architecture with a suite of representation-level metrics and causal interventions to probe how parallel streams…