HFEPX Hub
Updated from current HFEPX corpus (Feb 26, 2026). 64 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Frequently cited benchmark: retrieval. Common metric signal: accuracy. Newest paper in this set is from Feb 25, 2026.
Human Feedback Mix
Evaluation Modes
Top Benchmarks
Top Metrics
Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li · Feb 25, 2026 · Citations: 0
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 · Feb 25, 2026 · Citations: 0
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.
Hyo Jin Kim · Feb 25, 2026 · Citations: 0
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.
Zhijiang Tang, Linhua Wang, Jiaxin Qi, Weihao Jiang, Peng Hou · Feb 25, 2026 · Citations: 0
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.
Mengxuan Hu, Vivek V. Datla, Anoop Kumar, Zihan Guan, Sheng Li · Feb 24, 2026 · Citations: 0
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).
Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis · Feb 24, 2026 · Citations: 0
However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs.
Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao · Feb 24, 2026 · Citations: 0
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.
Chenyang Zhao, Vinny Cahill, Ivana Dusparic · Feb 24, 2026 · Citations: 0
Preference-based RL offers an appealing alternative by learning from human preferences over pairs of behavioural outcomes.
Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar · Feb 24, 2026 · Citations: 0
Reward models play a fundamental role in aligning large language models with human preferences.
Wanyong Feng, Andrew Lan · Feb 23, 2026 · Citations: 0
We train the model in a two-step process, first via Supervised Fine-Tuning and then via preference optimization for knowledge-response alignment.
Maryam Amirizaniani, Alireza Salemi, Hamed Zamani · Feb 22, 2026 · Citations: 0
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context.
Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov · Feb 21, 2026 · Citations: 0
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
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
Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar · Feb 20, 2026 · Citations: 0
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.
Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn · Feb 20, 2026 · Citations: 0
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.
Aaron Louis Eidt, Nils Feldhus · Feb 20, 2026 · Citations: 0
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.
Iskar Deng, Nathalia Xu, Shane Steinert-Threlkeld · Feb 19, 2026 · Citations: 0
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.
Faria Huq, Zora Zhiruo Wang, Zhanqiu Guo, Venu Arvind Arangarajan, Tianyue Ou · Feb 19, 2026 · Citations: 0
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold.
Serin Kim, Sangam Lee, Dongha Lee · Feb 19, 2026 · Citations: 0
Large language models have advanced web agents, yet current agents lack personalization capabilities.
Yuyan Bu, Xiaohao Liu, ZhaoXing Ren, Yaodong Yang, Juntao Dai · Feb 18, 2026 · Citations: 0
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment.
Mengjie Qian, Guangzhi Sun, Mark J. F. Gales, Kate M. Knill · Feb 18, 2026 · Citations: 0
Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements.
Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen · Feb 18, 2026 · Citations: 0
Existing evaluations of agents with memory typically assess memorization and action in isolation.
Kaiqu Liang, Julia Kruk, Shengyi Qian, Xianjun Yang, Shengjie Bi · Feb 18, 2026 · Citations: 0
Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users.
Mehrab Beikzadeh, Yasaman Asadollah Salmanpour, Ashima Suvarna, Sriram Sankararaman, Matteo Malgaroli · Feb 17, 2026 · Citations: 0
While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to balance patient preferences with clinical safety.
Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Rosé · Feb 17, 2026 · Citations: 0
In practice, users iteratively refine visualizations through multi-turn interactions that require maintaining common ground, tracking prior edits, and adapting to evolving preferences.
Roksana Goworek, Haim Dubossarsky · Feb 17, 2026 · Citations: 0
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
Mohammad Aflah Khan, Mahsa Amani, Soumi Das, Bishwamittra Ghosh, Qinyuan Wu · Feb 17, 2026 · Citations: 0
Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms.
Xiaoze Liu, Ruowang Zhang, Weichen Yu, Siheng Xiong, Liu He · Feb 17, 2026 · Citations: 0
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
Austin Veselka · Feb 16, 2026 · Citations: 0
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
Avinandan Bose, Shuyue Stella Li, Faeze Brahman, Pang Wei Koh, Simon Shaolei Du · Feb 16, 2026 · Citations: 0
Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available.
Shiwei Hong, Lingyao Li, Ethan Z. Rong, Chenxinran Shen, Zhicong Lu · Feb 16, 2026 · Citations: 0
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.
Kenichi Fujita, Yusuke Ijima · Feb 15, 2026 · Citations: 0
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'').
Sher Badshah, Ali Emami, Hassan Sajjad · Feb 13, 2026 · Citations: 0
Large language models (LLMs) are increasingly used as judges to replace costly human preference labels in pairwise evaluation.
Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao · Feb 11, 2026 · Citations: 0
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.
Preni Golazizian, Elnaz Rahmati, Jackson Trager, Zhivar Sourati, Nona Ghazizadeh · Feb 10, 2026 · Citations: 0
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
Jingyi Xu, Xingyu Ren, Zhoupeng Shou, Yumeng Zhang, Zhiqiang You · Jan 24, 2026 · Citations: 0
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.
Zhitao He, Zongwei Lyu, Yi R Fung · Jan 22, 2026 · Citations: 0
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
Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz · Jan 14, 2026 · Citations: 0
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
Dilara Torunoğlu-Selamet, Dogukan Arslan, Rodrigo Wilkens, Wei He, Doruk Eryiğit · Jan 13, 2026 · Citations: 0
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.
Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu, Pinyi Zhang · Jan 12, 2026 · Citations: 0
Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs).
Laya Iyer, Kriti Aggarwal, Sanmi Koyejo, Gail Heyman, Desmond C. Ong · Jan 9, 2026 · Citations: 0
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.
Anantha Sharma · Jan 3, 2026 · Citations: 0
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
Jonathan Kamp, Roos Bakker, Dominique Blok · Dec 11, 2025 · Citations: 0
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.
David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu · Nov 7, 2025 · Citations: 0
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
Qiusi Zhan, Hyeonjeong Ha, Rui Yang, Sirui Xu, Hanyang Chen · Oct 31, 2025 · Citations: 0
Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs.
Ran Xu, Jingjing Chen, Jiayu Ye, Yu Wu, Jun Yan · Oct 27, 2025 · Citations: 0
Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation.
Anubhav Jangra, Smaranda Muresan · Oct 24, 2025 · Citations: 0
Using the best performing LLM as the backbone of a quantitative study with 41 participants, we uncover distinct user preferences across hinting strategies, and identify the limitations of automatic evaluation metrics to capture them.
Ruochen Mao, Yuling Shi, Xiaodong Gu, Jiaheng Wei · Oct 23, 2025 · Citations: 0
Aligning large language models with human preferences is critical for creating reliable and controllable AI systems.
Rongzhi Zhang, Liqin Ye, Yuzhao Heng, Xiang Chen, Tong Yu · Oct 14, 2025 · Citations: 0
Finally, we demonstrate efficiency enhancements across three downstream tasks: preference data synthesis, Pareto frontier approximation and optimization, and distillation of aligned behaviors for intervention-free inference.
Zixin Song, Bowen Zhang, Qian-Wen Zhang, Di Yin, Xing Sun · Oct 5, 2025 · Citations: 0
On the official C-STS benchmark, PoLi-RL achieves a Spearman correlation coefficient of 48.18, establishing a new SOTA for the cross-encoder architecture.
Yucheng Wang, Yifan Hou, Aydin Javadov, Mubashara Akhtar, Mrinmaya Sachan · Sep 28, 2025 · Citations: 0
These inconsistencies stem from a lack of controlled evaluation frameworks and analysis of models' internals to isolate when and why modality interactions support or undermine reasoning.
Jiho Kim, Junseong Choi, Woosog Chay, Daeun Kyung, Yeonsu Kwon · Sep 26, 2025 · Citations: 0
In our simulation environment, a user agent with a rich persona interacts with the assistant, providing ratings on how well each suggestion aligns with its preferences and context.
Yunqing Liu, Nan Zhang, Zhiming Tan · Sep 1, 2025 · Citations: 0
We additionally contribute a CAD dataset with human preference annotations.
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin · Aug 16, 2025 · Citations: 0
Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified.
Renren Jin, Tianhao Shen, Xinwei Wu, Dan Shi, Haoran Sun · Jun 30, 2025 · Citations: 0
Conducting supervised and preference fine-tuning of large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human preferences and values.
Kaja Dobrovoljc · May 28, 2025 · Citations: 0
Results show that, across both languages, spoken corpora contain fewer and less diverse syntactic structures than their written counterparts, with consistent cross-linguistic preferences for certain structural types across modalities.
Yuchen Yan, Jin Jiang, Zhenbang Ren, Yijun Li, Xudong Cai · May 21, 2025 · Citations: 0
However, existing reward benchmarks focus on preference comparisons between responses rather than evaluating verification against ground truth references, leaving a critical gap in our ability to evaluate verification systems used in reason
Zhanliang Wang, Da Wu, Quan Nguyen, Zhuoran Xu, Kai Wang · May 9, 2025 · Citations: 0
To address this challenge, we introduce MINT (Multimodal Integrated kNowledge Transfer), a framework that aligns unimodal large decoder models with domain-specific decision patterns from multimodal biomedical data through preference optimiz
Zheng Hui, Xiaokai Wei, Yexi Jiang, Kevin Gao, Chen Wang · Apr 26, 2025 · Citations: 0
These domains typically involve fixed content and passive consumption, where user preferences can be matched by genre or theme.
Haohao Qu, Shanru Lin, Yujuan Ding, Yiqi Wang, Wenqi Fan · Apr 16, 2025 · Citations: 0
Specifically, ContRec consists of two key modules: a sigma-VAE Tokenizer, which encodes users/items with continuous tokens; and a Dispersive Diffusion module, which captures implicit user preference.
