Proposes the nine-dimensional Meaning Intelligence Framework (MIF) to distinguish surface sentiment from true intent in Nigerian discourse; zero-shot accuracy 33.3%, schema-guided 73.3%.

Celestine Achi

Proposes Turing-RL, a reinforcement learning approach using discriminative Turing rewards to train human user simulators, outperforming traditional response matching methods.

Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu et al.

RubricsTree constructs a hierarchical Boolean rubric system guided by expert-curated clinical criteria, enabling scalable, expert-aligned evaluation with over 100 atomic metrics, surpassing industry baselines.

Weizhi Zhang, Zechen Li, Hamid Palangi et al.

This study benchmarks 12 LLM pipeline configurations on MetaSyn, revealing a screening bottleneck with a maximum recall of 52.7% despite 90.9% retrieval recall at K=200.

Anzhe Xie, Weihang Su, Yujia Zhou et al.

Proposes a method combining lexical token analysis and multi-word similarity to quantify cultural localization in AI-generated stories, revealing only 9-17% of vocabulary accounts for cultural differences.

Shaily Bhatt, Supriti Vijay, Jeremiah Milbauer et al.

Introduces operads as a formal framework for question decomposition, with operadic consistency correlating strongly with model accuracy across multiple datasets.

Nathaniel Bottman, Kyle Richardson

VISTA introduces a hybrid user simulator combining UI and API actions, with six metrics for realism and coverage, outperforming existing methods in diverse scenarios.

Yunan Lu, Ryan Shea, Yusen Zhang et al.

This paper reveals that RLHF achieves shallow alignment by compressing partisan signals without removing the underlying partisan structure, as shown through internal representation analysis of Llama 3.1 8B.

Wendy K. Tam

AdvGRPO framework combines dense multi-channel rewards and advantage decoupling for joint attacker-defender training, achieving over 90% attack success rate and superior defense robustness.

Blake Bullwinkel, Eugenia Kim, Amanda Minnich et al.

Agentopia introduces a long-term multi-agent society simulation over 10 years, leveraging life reward-based reinforcement learning to enhance social behaviors and anthropomorphic capabilities of LLMs.

Xintao Wang, Sirui Zheng, Hongqiu Wu et al.

Proposes EmbedFilter, a linear transformation that filters the latent subspace encoding high-frequency, uninformative tokens, improving zero-shot text embedding performance by up to 14%.

Songhao Wu, Zhongxin Chen, Yuxuan Liu et al.

This paper introduces LLM-guided MAP-Elites evolution for optimizing medical decision pipelines, improving accuracy and safety metrics significantly across tasks.

Ivan Sviridov, Artem Oskin, Ivan Panin et al.

Proposes emergent language in multi-agent RL to study consciousness-related structures without prior biases, revealing self-referential communication and echo-mismatch circuits.

Zengqing Wu, Chuan Xiao

Introduced a benchmark for data snapshot detection, evaluated open-source models, revealing significant gaps in real-world institutional document understanding.

AJ Carl P. Dy, Aivin V. Solatorio

SubFit introduces non-contiguous submodule replacement in LLMs, achieving superior compression with 84.6% accuracy at 25% sparsity, using residual fitting without retraining.

Elia Cunegatti, Marcus Vukojevic, Erik Nielsen et al.

Proposed Script-Normalized WER (SN-WER), reducing script mismatch inflation by up to 12% across five Indic languages, enhancing multi-script ASR evaluation accuracy.

Priyaranjan Pattnayak

SimSD employs a plug-and-play masking strategy to enable token-level speculative decoding in diffusion LLMs, achieving up to 7.46× speedup while maintaining quality.

Junxia Cui, Haotian Ye, Runchu Tian et al.

LongTraceRL enhances long-context reasoning by generating complex multi-hop questions via knowledge graph random walks, using search trajectories for layered distractors, and entity-level rubric rewards, achieving significant improvements.

Nianyi Lin, Jiajie Zhang, Lei Hou et al.

This paper introduces the 'Disagreeing Rationales' framework, systematically analyzing how diverse human annotations and explanations impact hate speech detection, emphasizing the benefits of soft labels and rationales.

Benedetta Muscato, Beiduo Chen, Gizem Gezici et al.

This study introduces a multi-turn multi-agent dialogue framework to evaluate VLMs in spatial reasoning, showing limited improvements mainly due to visual grounding challenges.

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen