Academic

Academic · 1 min

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

arXiv:2604.02795v1 Announce Type: new Abstract: Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction …

Tianze Xu, Yanzhao Zheng, Pengrui Lu, Lyumanshan Ye, Yong Wu, Zhentao Zhang, Yuanqiang Yu, Chao Ma, Jihuai Zhu, Pengfei Liu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu

19 views Apr 6

Academic · 1 min

When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs

arXiv:2604.02778v1 Announce Type: new Abstract: Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge …

Linyu Li, Zhi Jin, Yichi Zhang, Dongming Jin, Yuanpeng He, Haoran Duan, Gadeng Luosang, Nyima Tashi

8 views Apr 6

Academic · 1 min

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models

arXiv:2604.02772v1 Announce Type: new Abstract: Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to …

Haoyu Liang, Peijian Zeng, Wentao Huang, Aimin Yang, Dong Zhou

11 views Apr 6

Academic · 1 min

Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts

arXiv:2604.02713v1 Announce Type: new Abstract: Conversational AI is increasingly deployed in emotionally charged and ethically sensitive interactions. Previous research has primarily concentrated on emotional benchmarks …

Jiawen Deng, Wentao Zhang, Ziyun Jiao, Fuji Ren

17 views Apr 6

Academic · 1 min

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

arXiv:2604.02709v1 Announce Type: new Abstract: The formal reasoning capabilities of LLMs are crucial for advancing automated software engineering. However, existing benchmarks for LLMs lack systematic …

Yihong Dong, Xiaoha Jian, Xue Jiang, Xuyuan Guo, Zhiyuan Fan, Jiaru Qian, Kechi Zhang, Jia Li, Zhi Jin, Ge Li

19 views Apr 6

Academic · 1 min

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints

arXiv:2604.02699v1 Announce Type: new Abstract: A previous study reported that E-Prime (English without the verb "to be") selectively altered reasoning in language models, with cross-model …

Rodney Jehu-Appiah

17 views Apr 6

Academic · 1 min

Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments

arXiv:2604.02669v1 Announce Type: new Abstract: How biased is a language model? The answer depends on how you ask. A model that refuses to choose between …

Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi

12 views Apr 6

Academic · 1 min

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

arXiv:2604.02668v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model's opinion. While …

Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah, Krishna Agaram, Ritwik Garg, Sagar Jha, Nimet Beyza Bozdag, Dilek Hakkani-Tur

18 views Apr 6

Academic · 1 min

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

arXiv:2604.02660v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for …

Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi

10 views Apr 6

Academic · 1 min

Revealing the Learning Dynamics of Long-Context Continual Pre-training

arXiv:2604.02650v1 Announce Type: new Abstract: Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of …

Yupu Liang, Shuang Chen, Guanwei Zhang, Shaolei Wang, Suncong Zheng

29 views Apr 6

Academic · 1 min

Speaking of Language: Reflections on Metalanguage Research in NLP

arXiv:2604.02645v1 Announce Type: new Abstract: This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP …

Nathan Schneider, Antonios Anastasopoulos

6 views Apr 6

Academic · 1 min

Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework

arXiv:2604.02640v1 Announce Type: new Abstract: Performance evaluation of Retrieval-Augmented Generation (RAG) systems within enterprise environments is governed by multi-dimensional and composite factors extending far beyond …

Kenichirou Narita, Siqi Peng, Taku Fukui, Moyuru Yamada, Satoshi Munakata, Satoru Takahashi

8 views Apr 6

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models

Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints

Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

Revealing the Learning Dynamics of Long-Context Continual Pre-training

Speaking of Language: Reflections on Metalanguage Research in NLP

Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework

JCG, PC

HSOLLC Co., Ltd.