4arXiv cs.CL (Computation and Language)·
FinKG-News: Knowledge graph framework for evidence-grounded credit risk report generation
Researchers introduce FinKG-News, a framework that constructs news-centric financial knowledge graphs by extracting events linked to companies, then uses these graphs as grounded evidence for in-context learning to generate credit risk reports. The system is evaluated across three financial dimensions and outperforms baselines by 19-34% on quality metrics while reducing hallucinations. A notable finding is that automated hallucination detection and quality assessment remain unreliable for this domain, requiring expert judgment. Code and resources are publicly released.
Related guides (1)
Related events (8)
KG grounding helps LLMs only for out-of-training knowledge: controlled clinical QA study
A new arXiv paper investigates when knowledge-graph (KG) grounding improves LLM performance on clinical question answering, finding that structured KG retrieval over the public biomedical graph PrimeKG provides no meaningful improvement on MedQA (all deltas ≤3.4) because the relevant facts are already in the model's training data. On synthetic counterfactual and hybrid benchmarks containing genuinely novel facts, the same pipeline lifts out-of-training accuracy from chance to ~100%. The paper also reproduces and partially corrects a recent Nature Medicine study on frontier LLMs vs. clinical RAG tools, flagging a score-deflating grader bug and clarifying that the reported ~88 HealthBench score reflects the Consensus variant, not full HealthBench (~46-47). The core finding — that RAG/KG grounding pays off only when the decisive fact is outside the model's training distribution — has direct implications for when retrieval augmentation is worth deploying.
ChronoMedKG: Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
ChronoMedKG is a new biomedical knowledge graph containing 460,497 evidence-linked triples across 13,431 diseases, each annotated with temporal components such as onset window and progression stage. It is constructed via a multi-agent pipeline using multiple frontier LLMs extracting from PubMed/PMC, with multi-model consensus and credibility filtering. The accompanying ChronoTQA benchmark (3,341 questions) reveals frontier LLMs lose ~30 points on temporal vs. static clinical questions, while ChronoMedKG-based retrieval recovers 47–65% of long-tail failures compared to 17–29% for HPOA-RAG. The work addresses a significant gap in existing KGs (PrimeKG, Hetionet, iKraph) that treat disease associations as static facts.
Agents-K1: End-to-end knowledge orchestration pipeline for agent-native scientific knowledge graphs
Agents-K1 is a new pipeline that converts raw scientific documents into structured knowledge graphs for use by LLM-based research agents, addressing the gap where existing systems reduce papers to abstracts and flat citation edges. The system integrates a multimodal parser, a 4B information-extraction model trained with GRPO, and a tri-source agent interface combining web search, graph retrieval, and cross-document traversal. The authors process 2.46 million scientific papers to produce Scholar-KG, releasing a one-million-paper subset. Experiments show improvements in scientific information extraction, knowledge graph construction, and multi-hop reasoning.
KnowsTFM: Knowledge graph-informed fine-tuning of small tabular foundation models
A new arXiv preprint introduces KnowsTFM, a method for fine-tuning small tabular foundation models (nanoscale TabPFN and TabICL variants) using structural attention priors derived from knowledge graphs and parameter-efficient low-rank updates. The approach targets niche domains with scarce, high-dimensional data shifted from pretraining distributions, showing meaningful gains in specialist settings but marginal gains on general tasks. The paper also reports that continual fine-tuning of frontier tabular models can trigger collapse of pretrained knowledge, a notable failure mode.
KINA: 899-item knowledge benchmark across 261 disciplines with formal representativeness and annotation incentive guarantees
KINA (Knowledge Index of Noah's Ark) is a new 899-item LLM benchmark spanning 261 fine-grained disciplines, addressing three methodological weaknesses in existing knowledge benchmarks: poor disciplinary representativeness, flat-payment annotation incentives, and unaudited ranking instability. The authors provide formal results: a (1-1/e) greedy approximation for disciplinary coverage and a proof that bonus-on-bar tournament payment weakly dominates flat payment for annotation quality. Evaluating 42 models from 13 labs, the top performer Gemini-3.1-Pro-Preview reaches 53.17%, with Claude-Opus-4.6 and GPT-5.4 close behind, revealing a tiered rather than smooth leaderboard structure with substantial headroom below saturation.
Peak-Then-Collapse: RLVR Tool-Use Failures on Knowledge-Graph APIs
This paper investigates RLVR-based tool-use training (GRPO on Qwen2.5-7B-Instruct) on a minimal knowledge-graph API (Freebase over Complex WebQuestions) and documents a 'peak-then-collapse' pattern where tool-grounded answer rates rise then fall to zero within 50 steps, replicated across four seeds and seven reward designs. The authors identify a key structural difference between knowledge-graph APIs and other tool types (Python, web search, JSON): sparse, non-natural-language feedback signals (e.g., empty brackets '[]') prevent the model from recovering via pretraining-familiar error signals. A direct oracle ablation shows relation selection is not the bottleneck—95.4% of errors are retrieval-composition failures—and self-distillation reaches 40% EM at 7B, with capacity scaling to 14B yielding only marginal gains, suggesting an interface-bound ceiling.
Two-stage LLM system extracts fine-grained events from 292K SEC 8-K filings with grounded citations
Researchers present a two-stage LLM pipeline that classifies SEC Form 8-K filings against a 119-type event taxonomy, anchoring every label to a verbatim quote via fuzzy n-gram validation and re-scoring each citation for quality. Applied to 292,984 filings from 2022–2026, the system produces 601,088 grounded event tags with precision rising from 12% to 96% as quality scores increase. The authors release the tagged dataset and validate economic signal via an event study on abnormal returns, confirming the taxonomy captures economically distinct events that the SEC's coarse item codes conflate.
RSF-GLLM: Differentiable graph reasoning framework for multi-hop knowledge graph QA
RSF-GLLM is a new framework for multi-hop question answering over knowledge graphs that decouples differentiable graph reasoning from LLM-based answer generation. The core Recurrent Soft-Flow (RSF) module uses a GRU-guided query updater with dynamic gating to traverse semantically dissimilar bridge nodes, with flow sparsity regularization guaranteeing convergence to discrete reasoning paths. Extracted paths are textualized to fine-tune an LLM, grounding generation in factual graph topology. Experiments on WebQSP and CWQ benchmarks show competitive accuracy with improved inference efficiency over LLM-heavy baselines.