arXiv AI
Aug 5
Reversing Arrows in Large Language Models
arXiv:2608. 03512v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks.
ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation
Related stories
arXiv AI
Jun 9
Implicit Causal Graph Construction in Text via Chain Discovery
arXiv:2606. 07525v1 Announce Type: cross Abstract: Causal graphs in text are typically populated by observable, predefined events.
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.
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.
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.
arXiv Computation and Language
Sep 16
SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP
SciNLP is a new benchmark dataset for full‑text entity and relation extraction in the NLP domain, comprising 60 manually annotated papers with 6,429 entities and 1,649 relations. It is the first dataset to provide full‑text annotations of entities and their relationships specifically for NLP literature. Experiments show that models trained on SciNLP outperform baselines on certain tasks, and the dataset enabled the automatic construction of a fine‑grained knowledge graph with an average node degree of 3.3.
arXiv Computation and Language
Oct 27
Towards a Learnable Retriever for Textual Graph Question Answering
arXiv:2610.33511v1 Announce Type: new Abstract: Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to groun...
arXiv Computation and Language
Oct 23
An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks
The paper evaluates recent large language models (LLMs) for knowledge graph-to-text generation against traditional fine‑tuned encoder‑decoder models. Using both reference‑based metrics and graph‑grounded, reference‑free LLM‑based evaluation, the authors find that LLMs close the performance gap on reference metrics and outperform fine‑tuned models on graph‑grounded metrics. The study also shows that LLM‑based evaluation scores correlate poorly with reference metrics, indicating they assess different aspects of quality, and that prompted LLMs produce fewer contradictions and omissions, especially as graph size increases.
arXiv AI
Jun 16
Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?
arXiv:2606. 15412v1 Announce Type: cross Abstract: Biomedical relation extraction (BioRE) is a key step in transforming biomedical literature into structured knowledge.
arXiv AI
Jun 24
Ensemble Learning for Large Language Models in Text and Code Generation: A Survey
arXiv:2503. 13505v3 Announce Type: replace-cross Abstract: Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation.
arXiv AI
Sep 1
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
The paper introduces LLM‑PeerReview, an unsupervised ensemble method that selects the best response from multiple LLM-generated candidates by scoring each answer with several LLMs, aggregating those scores via averaging or a graphical model, and choosing the highest-scoring response. The approach is peer‑review inspired, transparent, and interpretable, and it outperforms the Smoothie‑Global model by 6.9%–7.3% across factual recall QA, math reasoning, and instruction‑following tasks. The authors also provide a curated benchmark suite of 12 ensemble methods evaluated on four datasets and three task families to aid reproducibility.
arXiv Computation and Language
Aug 25
ConvergeWriter: Data-Driven Bottom-Up Article Construction
ConvergeWriter introduces a bottom‑up, data‑driven framework for long‑form document generation that first retrieves exhaustive knowledge from a source corpus and clusters it into distinct knowledge groups. These clusters then guide the creation of a hierarchical outline and the final text, ensuring the output is strictly grounded in the retrieved material and traceable to its sources. Experiments on 14B and 32B LLMs show that this approach matches or surpasses state‑of‑the‑art baselines, especially in scenarios requiring high factual fidelity and structural coherence.