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
Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu, James Kwok · Feb 25, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
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.
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.
The framework therefore provides a unified structural account of both human silence under pressure and AI preference-driven distortion.
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.
Because human annotations reflect subjective preferences and expertise, ground-truth captions are often incomplete or even incorrect, which in turn limits caption models.
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).
We construct and release a novel Chain-of-Thought (CoT) fine-tuning dataset that includes both utility-oriented and safety-critical prompts with step-by-step rationales.
Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis · Feb 24, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs.
Our findings on synthetic graphs and molecular benchmarks reveal that MAs do not preferentially concentrate on curvature extremes, despite their theoretical link to information flow.
Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao, Binbin Cao · Feb 24, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsCoding
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.
While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors an
Chenyang Zhao, Vinny Cahill, Ivana Dusparic · Feb 24, 2026 · Citations: 0
Pairwise PreferenceRlaif Or Synthetic FeedbackHuman EvalGeneral
Preference-based RL offers an appealing alternative by learning from human preferences over pairs of behavioural outcomes.
More recently, RL from AI feedback (RLAIF) has demonstrated that large language models (LLMs) can generate preference labels at scale, mitigating the reliance on human annotators.
Reward models play a fundamental role in aligning large language models with human preferences.
Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and generative judging models, which offer richer reasoning at the cost of higher computational ove
Maryam Amirizaniani, Alireza Salemi, Hamed Zamani · Feb 22, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context.
By optimizing multi-turn reasoning trajectories under a personalized reward function, the framework reinforces reasoning paths that better align with user-specific preferences and contextual signals reflected by the reward model.
Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov · Feb 21, 2026 · Citations: 0
Pairwise PreferenceHuman EvalGeneral
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.
Abraham Paul Elenjical, Vivek Hruday Kavuri, Vasudeva Varma · Feb 21, 2026 · Citations: 0
Pairwise PreferenceHuman EvalMathMedicine
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
Across diverse reasoning and diagnostic benchmarks (GSM8K, CRUXEval, MBPP, AIME, CorrectBench, and TruthfulQA) using Llama-3 and Qwen-3 (8B), explicit regulatory structuring substantially improves error diagnosis and yields a threefold incr
Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar · Feb 20, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsCoding
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.
As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deployment.
Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn · Feb 20, 2026 · Citations: 0
Pairwise PreferenceHuman EvalGeneral
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.
We address this challenge through a dual-scale validation framework applied to political stance prediction in argumentative discourse, combining pointwise and pairwise human annotation.
Aaron Louis Eidt, Nils Feldhus · Feb 20, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
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.
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.
Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments.
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold.
However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation.
Serin Kim, Sangam Lee, Dongha Lee · Feb 19, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsCoding
Large language models have advanced web agents, yet current agents lack personalization capabilities.
Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user preferences and contexts.
