- 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.
- 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.
- RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
Daniel Yang, Samuel Stante, Florian Redhardt, Lena Libon, Parnian Kassraie · Feb 27, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Reward models are central to aligning large language models (LLMs) with human preferences.
- 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.
- Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
Hung Tran, Langston Nashold, Rayan Krishnan, Antoine Bigeard, Alex Gu · Mar 4, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Web Browsing
We introduce Vibe Code Bench, a benchmark of 100 web application specifications (50 public validation, 50 held-out test) with 964 browser-based workflows comprising 10,131 substeps, evaluated against deployed applications by an autonomous…
- 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.
- $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners
Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan · Mar 4, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks, V_1-Infer improves Pass@1 by up to 10% over pointwise verification and outperforms recent test-time scaling methods while being…
- 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.
- Same Words, Different Judgments: Modality Effects on Preference Alignment
Aaron Broukhim, Nadir Weibel, Eshin Jolly · Feb 26, 2026 · Citations: 0
Pairwise PreferenceRlaif Or Synthetic Feedback Automatic Metrics
Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences, but its application to speech remains underexplored.
- 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.
- CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation
Mohammed Baharoon, Thibault Heintz, Siavash Raissi, Mahmoud Alabbad, Mona Alhammad · Mar 6, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety.
- 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…
- Sabiá-4 Technical Report
Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás · Mar 10, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Tool Use
The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal…
- AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning
Nikolas Karafyllis, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos, Giorgos Stamou · Mar 4, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We present a winning three-stage system for SemEval 2026 Task~12: Abductive Event Reasoning that combines graph-based retrieval, LLM-driven abductive reasoning with prompt design optimized through reflective prompt evolution, and post-hoc…
- 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.
- PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses
Minki Hong, Eunsoo Lee, Sohyun Park, Jihie Kim · Mar 11, 2026 · Citations: 0
Pairwise PreferenceRubric Rating Automatic Metrics
We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses.
- Surgical Post-Training: Cutting Errors, Keeping Knowledge
Wenye Lin, Kai Han · Mar 2, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
While prior research emphasizes the role of on-policy data in mitigating forgetting, we uncover--and validate both theoretically and empirically--an overlooked yet critical mechanism: the implicit regularization inherent in Direct…
- 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
Building on this insight, we propose CAMEL, a confidence-gated reflection framework that performs a lightweight single-token preference decision first and selectively invokes reflection only for low-confidence instances.
- 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).
- Truth as a Compression Artifact in Language Model Training
Konstantin Krestnikov · Mar 12, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In the random-error setting, models strongly prefer correct completions in paired evaluation: 83.1% accuracy at balanced data and 67.0% even when correct rules appear in only 10% of the corpus.
- LLMs Can Infer Political Alignment from Online Conversations
Byunghwee Lee, Sangyeon Kim, Filippo Menczer, Yong-Yeol Ahn, Haewoon Kwak · Mar 11, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Due to the correlational structure in our traits such as identities, cultures, and political attitudes, seemingly innocuous preferences such as following a band or using a specific slang, can reveal private traits.
- Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
Punyajoy Saha, Sudipta Halder, Debjyoti Mondal, Subhadarshi Panda · Mar 7, 2026 · Citations: 0
Pairwise PreferenceRed Team Automatic Metrics
Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, difficult to scale,…
- From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring
Minh Hoang Nguyen, Vu Hoang Pham, Xuan Thanh Huynh, Phuc Hong Mai, Vinh The Nguyen · Mar 6, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning…
- When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
Amirabbas Afzali, Myeongho Jeon, Maria Brbic · Mar 5, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Building on this insight, we propose Confidence-Weighted Preference Optimization (CW-PO), a general framework that re-weights training samples by a weak LLM's confidence and can be applied across different preference optimization…
- LocalSUG: Geography-Aware LLM for Query Suggestion in Local-Life Services
Jinwen Chen, Shuai Gong, Shiwen Zhang, Zheng Zhang, Yachao Zhao · Mar 5, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
While LLMs offer strong semantic generalization, deploying them in local-life services introduces three key challenges: lack of geographic grounding, exposure bias in preference optimization, and online inference latency.
- MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization
Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani · Mar 3, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In this work, we propose Modality-Decoupled Direct Preference Optimization (MoD-DPO), a simple and effective framework for improving modality grounding in omni LLMs.
- RLHFless: Serverless Computing for Efficient RLHF
Rui Wei, Hanfei Yu, Shubham Jain, Yogarajan Sivakumar, Devesh Tiwari · Feb 26, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences.
- 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.
- 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.
- 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.
- 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.