The paper introduces Evidence-Aligned Entity Verification (EAEV), a method for detecting entity-level hallucinations in retrieval-augmented generation (RAG). EAEV aligns generated entities with retrieved evidence across three dimensions and uses counterfactual stability analysis to maintain robust alignments when evidence changes. Experiments on multiple RAG benchmarks show that EAEV consistently outperforms existing hallucination detection methods and generalizes well.
By Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang
The paper introduces WAPP, a framework for safely learning positive security Web Application Firewall (WAF) policies from live traffic. It combines trust filtering, deterministic rule synthesis, confidence scoring, and validation to protect against poisoned training data. Experiments on controlled applications show that WAPP improves poisoning resilience and blocks confirmed CRS bypasses, though free‑text fields still pose precision challenges.
By Heba Osama, Zeyad Ahmed, Mohamed Amgad, Ahmed Saafan, Jana Elfeky, Mariam Abdelati, Haitham Ghalwash
The paper introduces CodeTD, a novel method that uses topological data analysis of attention maps from code language models to pre‑execution assess code correctness and detect hallucinations. It quantifies prompt‑generation mismatch through topological patterns and is evaluated on multiple benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL‑E) across five programming languages and ten Code LLMs up to 34B parameters. Results show CodeTD outperforms recent baselines and transfers well between coding benchmarks.
By Daria Voronkova, Ilya Trofimov, Anton Dmitriev, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov
The paper reviews how large language models (LLMs) are being used to model social networks, highlighting their ability to represent users, relationships, and interactions through natural language. It categorizes existing work into network generative models—split into selection‑based and interaction‑based approaches—and dynamic process models, which cover opinion dynamics, information diffusion, and rumor propagation. The survey also discusses the advantages of LLMs for realistic, context‑aware social behavior, while noting limitations such as social biases and prompt sensitivity, and outlines open research challenges and future directions.
By Shikha Mallick, Alex Thomo, Akrati Saxena
NOAH is a generative transformer that learns the full multimodal patient journey by integrating bidirectional time and a variational latent space. Trained on over 559 million clinical events from 431,000 hospital visits, it processes medical images, time‑series, numeric signals, categorical events, and both structured and unstructured records. The model supports autoregressive forecasting, zero‑shot classification, and counterfactual intervention simulation, yielding strong performance on clinical outcomes, ICD chapters, comorbidities, and time‑to‑event prediction.
By Tobias Susetzky, Raphael Rehms, Dmitrii Seletkov, \"Ozg\"un Turgut, Michelle Espranita Liman, Lisa Steinhelfer, Rickmer Braren, Daniel Rueckert
Alpha‑R1 introduces a reinforcement‑learning aligned large language model framework that performs context‑aware alpha screening by semantically gating candidate factors against a dynamic market state description. The model, trained with group relative policy optimization using realized portfolio returns as reward, selects a sparse subset of factors whose economic rationale matches current market conditions. In a 12‑month out‑of‑sample test, Alpha‑R1 achieved annualized returns of 47.87% on the S&P 500 and 40.57% on the CSI 300, with Sharpe ratios of 1.62 and 2.23, demonstrating the effectiveness of semantic factor reranking in non‑stationary markets.
By Zuoyou Jiang, Li Zhao, Rui Sun, Ruohan Sun, Zhongjian Li, Jing Li, Daxin Jiang, Zuo Bai, Cheng Hua
The paper introduces TITAnD, a Trajectory Image Transformer that converts dense and sparse GPS trajectories into a Hyperspectral Trajectory Image (HTI) and applies vision-based classification and segmentation for anomaly detection. It employs a Cyclic Factorized Transformer (CFT) that splits attention along within-day and across-day axes, drastically reducing computational cost and enabling multi-month analysis. Empirical results show TITAnD outperforms existing sparse and dense benchmarks, achieving higher AUC-PR and faster inference than comparable Transformers.
By Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath
Edu-QuRating is a pipeline that scores and curates educational data across multiple dimensions—accuracy, engagement, structure, and audience appropriateness—using an LLM judge to label document pairs and distill these preferences into reusable Edu-QuRaters. The best Edu-QuRater achieves 91.7% accuracy against held‑out GPT‑4.1‑mini judgments and is applied to filter 322.25 M FineWeb‑Edu‑Fortified documents, improving small‑model pre‑training performance on nine benchmarks. Additionally, Edu-QuRater scores serve as reward signals in GRPO post‑training, yielding responses that are preferred for pedagogical quality and instruction following over the Qwen3‑4B base model.
By Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu, Mohamed Huti, Moritz Boos, Amy Waldock, Dominic Andrews, Paul Atherton
The paper introduces EvoTree, a staged framework for automatically generating evolution trees from citation graphs. It separates backbone learning from temporal refinement, using a graph-aware encoder and hierarchical clustering to build a stable taxonomy, then fine-tunes temporally to attach marginal papers under monotonic-path constraints, and finally labels concepts with an LLM without changing the topology. The authors release an annotated benchmark across 11 AI subfields and report that EvoTree outperforms baselines in NMI, citation-direction accuracy, concept purity, and marginal-paper detection.
By Zexing Zhao, Yuntong Hu, Liang Zhao
ROAM is a relation‑guided framework for managing atomic memories in long‑term language‑model agents. It classifies atom pairs as independent, equivalent, subsuming, or conflicting, then organizes observations into Primary and Evidence roles, fusing complementary details into compact views. Only Primary views are retrieved for answering, which reduces redundancy and improves answer accuracy by up to 29.8 percentage points across models and settings.
By Jianjie Zheng, Peng Lai, Sijie Cheng, Jiehui Zhao, Lei Yang, Guanhua Chen
The paper introduces a framework that combines a Geometric Vision Parser and a Symbolic Solver to enable a Large Language Model to solve complex plane geometry problems. By translating diagrams into symbolic representations and performing formal deductions, the approach reduces hallucinations and produces interpretable, human-like solutions. Experiments on a new benchmark from 2025 Chinese Zhongkao exams show performance comparable to Gemini 2.5 Pro.
By Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou, Yan Cao, Xin Shen, Dongcai Lu, Yi Zhou
arXiv:2605.22286v2 Announce Type: replace-cross
Abstract: Text-based counseling provides a valuable source of information for assessing depression severity. We study prediction of the total score on...
By Zhaomin Wu, Jiayi Li, Bingsheng He
VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.
By Zhe Gao, Shiyu Shen, Taifeng Chai, Weinong Wang, Haotian Xu, Xing Wu, Wenbin Li, Qi Fan, Yang Gao, Dacheng Tao
The paper introduces OSOL, a method for mitigating higher‑order interference in multi‑domain reinforcement learning. OSOL selects a focus domain each iteration, uses token‑level footprints from the previous checkpoint to rank rebound risk, and applies an adaptively scaled correction to the GRPO update. Experiments on Qwen3‑30B‑A3B show a 5.7% improvement over the best baseline without higher‑order differentiation.
By Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Guojun Yin, Wei Lin, Ran He
The paper introduces 3DWay, a method that predicts 3D-consistent waypoints for robot manipulation by first generating multi‑view consistent 2D waypoints and then triangulating them. This approach addresses the 3D ambiguity inherent in 2D trajectory predictions and leverages pretrained vision‑language models to provide explicit 3D motion specifications. Experiments demonstrate that 3DWay improves 3D spatial grounding and vision‑language reasoning, enhancing generalization for robot manipulation tasks.
By Ziqin Huang, Yingyue Li, Chenyangguang Zhang, Ruida Zhang, Yuxin Chen, Gu Wang, Xingyu Liu, Masayoshi Tomizuka, Xiangyang Ji
The study examines how the design of audit questions influences perceived bias in large language models (LLMs). Using 40,726 requests across five models and three domains—hiring, lending, and medical triage—the authors find that demographic bias effects are not replicated when the audit is standardized. Instead, the audit’s construction, such as question phrasing and ordering, has a stronger impact on model responses than applicant demographics.
By Siddharth Vohra, Manikandan Ravikiran
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
The paper investigates how a defendant’s courtroom statement influences decisions made by large language model (LLM)–simulated jurors. Using the newly introduced JuryBench benchmark, the authors analyze 432,000 verdicts from 20 frontier LLMs, varying defendant background, emotional appeal, and rebuttal content. Results show that emotional persuasion can backfire, that jurors are harsher toward defendants from different backgrounds and more lenient toward same‑background defendants, and that juror ideology strongly shapes verdict severity.
By Cho-Ying Wu
The paper introduces a decision‑theoretic framework that elicits both probability judgments and decisions from large language models (LLMs) to test whether their reported beliefs are consistent with their actions. It shows that this framework yields empirically testable conditions without assuming a specific utility function. In clinical diagnosis simulations, the authors find that while LLMs’ reported beliefs are not perfect reflections of the information in their decisions, the discrepancies are small for the strongest models.
By Khurram Yamin, Jingjing Tang, Santiago Cortes-Gomez, Amit Sharma, Eric Horvitz, Bryan Wilder
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra