arXiv Computation and Language

Kongzi: A Historical Large Language Model with Fact Enhancement

Kongzi is a historical large language model that enhances factual accuracy through continued pre‑training on historical corpora, supervised fine‑tuning, and fact‑enhanced reinforcement learning. Its reward system compares entities and relations in generated responses with historical references via knowledge‑graph similarity. Evaluations on 0.5B and 7B models show that Kongzi‑7B achieves the highest historical‑accuracy ratings among compared models and that reinforcement learning improves answer scores and CMMLU‑Chinese‑History accuracy, though it still falls short of the strongest baselines.

arXiv AI

Sep 10

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

The paper introduces Fact-Ablated Evaluation (FAE), a framework that iteratively removes cited evidence to test whether large language models (LLMs) adjust their fact‑checking predictions accordingly. Experiments reveal that many off‑the‑shelf LLMs rely more on internal knowledge than on the provided evidence. To address this, the authors propose REAL, a training method that uses counterfactual evidence supervision to encourage LLMs to base veracity judgments on evidence, achieving better evidence‑dependent performance across four datasets.

By Xingyu Deng, Mingzi Cao, Nikolaos Aletras, Xi Wang, Mark Stevenson

llms fine-tuning benchmarks

arXiv AI

Jul 21

DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration

arXiv:2607. 17935v1 Announce Type: cross Abstract: Automated fact-checking remains a challenge for Large Language Models (LLMs) due to "query brittleness" in traditional retrieval systems.

By Cong Hoan Nguyen, Thomas Hoang, Hieu Minh Duong, Long Nguyen

llms benchmarks

arXiv Machine Learning

Sep 10

Evaluation of Contextual Understanding in Large Language Models

arXiv:2609.09004v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understandi...

By Subavarshana Arumugam, Mamta Nallaretnam, Kithuni Wickramasinghe, Chamath Gunapala, Pragatheeswaran Vipulanandan, Uthayasanker Thayasivam, Kamal Premaratne

llms nlp benchmarks safety

arXiv AI

Jul 21

Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph

arXiv:2607. 17266v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing.

By Peiji Yu, Xin Chen, Tianxing Wu

llms agents nlp benchmarks safety

arXiv AI

Sep 10

Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models

The paper evaluates the scalability and adversarial generalization of Natural Language Inference (NLI) models trained with Group Relative Policy Optimization (GRPO) for Chain-of-Thought learning. By fine‑tuning 7B, 14B, and 32B language models with LoRA and QLoRA, the authors show strong performance on standard and adversarial NLI benchmarks, with the 32B model outperforming supervised baselines on adversarial sets. Using AWQ quantization, the 32B model fits within 22 GB of CUDA memory, demonstrating a scalable, practical framework for robust NLI without sacrificing inference quality.

By Pablo Miralles-Gonz\'alez, Javier Huertas-Tato, Alejandro Mart\'in, David Camacho

llms nlp reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jul 29

DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification

arXiv:2607. 25069v1 Announce Type: cross Abstract: Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning.

By Sagnik Sinha, Shreyas Shrestha

llms reinforcement-learning fine-tuning

arXiv AI

Sep 10

UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms

arXiv:2609.05910v1 Announce Type: cross Abstract: Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challeng...

By Peng Lai, Yichao Du, Junchao Wu, Weibo Gao, Linan Yue, Longyue Wang, Weihua Luo, Derek F. Wong, Guanhua Chen

llms reinforcement-learning benchmarks safety

arXiv AI

Aug 28

Co-Evolving Structured Knowledge and Reasoning in Language Models

The paper introduces KBevo, a co‑evolving framework that simultaneously builds a structured knowledge base and performs reasoning over it for knowledge‑intensive question answering. By optimizing both components end‑to‑end with QA outcome rewards, the system improves the quality and connectivity of the knowledge base, leading to higher answer reachability and better compositional factual reasoning. Compared to standard retrieval baselines, KBevo offers greater controllability and improved factual accuracy.

By Ryan Thomas Noonan, Linxi Zhao, Menghan Xu, Akanksha Sarkar, Mihir Mishra, Dongyoung Go, Kilian Q. Weinberger, Yoav Artzi, Jennifer J. Sun

llms rag nlp

arXiv AI

Jul 14

CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps

arXiv:2607. 10562v1 Announce Type: new Abstract: Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge.

By JungMin Yun, JuneHyoung Kwon, YoungBin Kim

llms nlp

arXiv AI

Oct 7

Reward on Path: Learning Intermediate Supervision Signals for Knowledge Graph Question Answering

arXiv:2605.10791v2 Announce Type: replace Abstract: Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent methods use supervision de...

By Shengxiang Gao, Chao Lei, Jey Han Lau, Linhao Luo, Jianzhong Qi

llms nlp reinforcement-learning efficiency

arXiv Machine Learning

Jul 28

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

arXiv:2602. 01348v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit.

By Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma

rag nlp reinforcement-learning benchmarks safety

arXiv Machine Learning

Aug 12

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.

By Yiyang Shen, Lifu Tu, Weiran Wang

llms reinforcement-learning fine-tuning efficiency

Related stories