The paper introduces VAKE, a two‑stage reinforcement‑learning framework that activates latent factual knowledge in large language models. In the Priming stage, the model explicitly inserts bridging triples into an insufficient subgraph, guided by rewards from a frozen model’s answers. The Reasoning stage then trains the model to answer from the original input, demonstrating that the elicitation capability transfers to implicit reasoning and consistently outperforms baselines across multiple benchmarks and model sizes.
By Zuocheng Ying, Yang Yang, Yumou Wu, Chuanbo Zhu, Jiarui Wang, Ziqi Wu, Jingming Cai, Junqing Yu, Zikai Song
arXiv:2610.07894v1 Announce Type: cross
Abstract: Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is in...
By Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Borui Jiang, Bo Han
arXiv:2609.24238v1 Announce Type: new
Abstract: We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contrad...
By Guilhem Fouilh\'e, Nicholas Asher, Philippe Muller
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso
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
arXiv:2607. 06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English.
By Andrea Alfarano, Andrea Bacciu, Saab Mansour, Amin Mantrach, Marcello Federico
arXiv:2606. 03969v1 Announce Type: cross Abstract: Reliable uncertainty communication is critical to the trustworthiness of LLMs, yet faithful calibration (FC)--the alignment between models' intrinsic and (linguistically) expressed confidence--is a persistent failure mode.
By Areeb Gani, Asal Meskin, Gabrielle Kaili-May Liu, Arman Cohan
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
The paper introduces LURCH, a benchmark of 6,550 question‑answering instances that quantifies long‑context reasoning difficulty using three properties: evidence scope, evidence dispersion, and reasoning depth. Experiments with both proprietary and open‑weight models show that these properties are strongly negatively correlated with performance, that performance drops sharply for dispersed evidence as context length grows, and that difficulty increases when multiple properties are high simultaneously. The study demonstrates that context length alone is insufficient to explain model failures, and that the new metrics provide a more nuanced understanding of long‑context challenges.
By Shiwen Qin, Cameron Barker, Henry Gouk, Elliot J. Crowley, Shay B. Cohen, Mirella Lapata, Miao Li
arXiv:2604.27251v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicite...
By Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata, Nikolaos Aletras
GRACE is a step‑level benchmark for evaluating the faithfulness of chain‑of‑thought reasoning over context. It provides human annotations for each step in CoT traces from 10 models across 4 datasets, labeling faithfulness, error category, and natural‑language explanations. The benchmark introduces a data‑driven taxonomy that splits errors into GRACE‑Inference (deductive) and GRACE‑Grounding (factual) tracks, each with four categories, and demonstrates that incorporating step‑level faithfulness signals can improve downstream accuracy and reasoning reliability.
By Hoang Pham, Dong Le, Anh Tuan Luu
CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.
By Jingguang Li, Yebo Wu, Zuyi Guo, Kailang Ma, Xianjie Dai, Han Zheng, Benwang Chen, Li Li, Can Rong, Heye Huang