arXiv AI

Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?

The paper redefines structured generation as an ambiguity‑aware inference problem, arguing that natural language often allows multiple valid structured outputs. It introduces a multi‑valid learning framework that preserves these alternatives during training and uses graph‑based reasoning to compare candidate structures based on semantic alignment and relational consistency. Experiments on benchmark datasets show that this approach improves accuracy, stability, and robustness compared to traditional single‑output methods.

arXiv Computation and Language

Sep 25

CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models

CONSISTRE is a consistency‑aware framework for document‑level relation extraction that tackles contradictions in large language model predictions. It offers two tracks: an inference‑time track that refines black‑box LLM outputs through constraint‑aware prompting, verification, and self‑reflection, and a training‑time track that distills consistency knowledge into smaller open‑source models via supervised fine‑tuning and reinforcement learning. Experiments on DocRED show both tracks outperform baselines, with the inference‑time track matching competitive F1 scores and the training‑time track narrowing the performance gap to proprietary LLMs while reducing inference cost.

By Mingxuan Sun

llms reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jul 17

CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning

arXiv:2607. 14114v1 Announce Type: cross Abstract: Graph learning under distribution shift presents a persistent challenge, where models adapt to new graphs with limited or even no supervision.

By Haohua Niu, Xingtong Yu, Yang Liu, Junfeng Fang, Xuanting Xie, Jie Tan, Zhongjian Zhang, Hong Cheng, Yuan Fang

llms benchmarks

Hugging Face Trending Papers

Jul 27

CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models

Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs.

llms reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jun 30

The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding

arXiv:2603. 03305v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable.

By Avinash Reddy, Thayne T. Walker, James S. Ide, Amrit Singh Bedi

llms benchmarks

arXiv AI

Jun 3

Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models

arXiv:2606. 03624v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously.

By Zhengyi Zhao, Shubo Zhang, Huimin Wang, Zezhong Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Yulan He, Kam-Fai Wong, Xian Wu

llms

arXiv AI

Aug 3

Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction

arXiv:2601. 15037v2 Announce Type: replace-cross Abstract: Open-domain Relational Triplet Extraction (ORTE) aims to mine structured knowledge without predefined relation schemas.

By Xiaonan Jing, Gongqing Wu, Xingrui Zhuo, Lang Sun, Jiapu Wang

llms benchmarks

arXiv Computation and Language

Sep 23

Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models

arXiv:2609.26610v1 Announce Type: new Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested...

By David Torres-Moreno, Jorge Hermosillo-Valadez

llms agents nlp

arXiv Machine Learning

Sep 2

Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning

arXiv:2609.01292v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks i...

By Oleksii Kolesnichenko, Jakub Pele\v{s}ka, Gustav \v{S}\'{\i}r

benchmarks data-engineering

arXiv Computation and Language

Oct 5

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning

arXiv:2511.07910v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enab...

By Songze Li, Zhiqiang Liu, Zhaoyan Gong, Xiaoke Guo, Zhongpu Bo, Zhengke Gui, Lei Liang, Huajun Chen, Wen Zhang

llms nlp benchmarks

Hugging Face Trending Papers

Jun 2

Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models

Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP).

llms

arXiv AI

Jun 26

Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes

arXiv:2509. 09960v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation is increasingly essential in machine learning, supporting downstream applications when real-world, high-quality tabular data is insufficient.

By Mingxuan Jiang, Keyang Chen, Yongxin Wang, Yongsheng Zhao, Ziyue Dai, Yicun Liu, Zeping Li, Qiuyang Zhang, Hongyi Nie, Hongbin Zhu, Sen Liu, Guangnan Ye, Hongfeng Chai

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jun 26

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

arXiv:2606. 26578v1 Announce Type: new Abstract: Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges.

By Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai, Tao Zhong, Mingxuan Yuan

llms agents reinforcement-learning fine-tuning

Related stories