The paper investigates how large language models (LLMs) engage with long-form narratives by comparing their generated novel summaries to human-authored ones. Researchers align sentences from 150 human-written summaries to specific chapters, highlighting the challenge of this alignment task and the complexity of summarization. They find stylistic differences and that LLMs tend to focus more on the ends of texts, suggesting insights into why models may struggle with narrative comprehension.
By Rebecca M. M. Hicke, Sil Hamilton, David Mimno, Ross Deans Kristensen-McLachlan
The paper introduces Fast MCTS, a Monte Carlo Tree Search approach for knowledge base question answering that replaces costly terminal rollouts with an information gain reward for intermediate states. This reward is computed using a question‑conditioned PPL‑ratio proxy over sanitized interaction histories, leveraging an open‑source instruction LLM without extra training. Experiments on four KBQA benchmarks demonstrate that Fast MCTS consistently outperforms linear baselines and improves the accuracy‑cost trade‑off compared to classic rollout‑based MCTS.
By Guanming Xiong, Haochen Li, Zonghong Dai, Liqiang Wen, Wen Zhao
The paper explores whether ChatGPT can predict stock market movements by analyzing Twitter sentiment. Using tweets about Microsoft and Google, the study finds a positive correlation between ChatGPT’s sentiment assessments and the subsequent stock performance of both companies. The results suggest that ChatGPT’s language understanding can translate social media sentiment into useful financial forecasts.
By Ummara Mumtaz, Summaya Mumtaz
The article presents a mathematical framework for large language models (LLMs), detailing how text sequences are encoded into tokens, how next‑token prediction architectures are defined, and how these models are trained and deployed for tasks such as summarization, recommendation, software writing, and quantitative problem solving. It emphasizes that the framework relies on basic concepts from information theory, probability, and optimization, yet captures the complex algorithmic structure responsible for LLMs’ empirical successes. The authors argue that this formalism enables the study of accuracy, efficiency, and robustness, and points toward new methodological developments.
By Ricardo Baptista, Andrew Stuart, Son Tran
The paper shows that language models trained on natural text develop number representations that exhibit periodic features with dominant periods at T = 2, 5, 10. It identifies a two‑tiered hierarchy: all models learn Fourier‑domain spikes at these periods, but only some acquire geometrically separable features that allow linear classification of numbers modulo T. The study demonstrates that data, architecture, optimizer, and tokenizer influence whether these separable features emerge, and that models can learn them either from co‑occurrence signals in language or from multi‑token addition tasks, illustrating convergent evolution across diverse models.
By Deqing Fu, Tianyi Zhou, Mikhail Belkin, Vatsal Sharan, Robin Jia
The paper investigates Retrieval-Augmented Generation fine‑tuning (RAG‑SFT) for generating requirements documents in electronics engineering, comparing two 7B models trained with different data strategies. It introduces a claim‑based evaluation pipeline, C‑FEX, and a new metric, Parametric Knowledge Precision (PKP), to assess factuality of model‑generated claims. Results show that fine‑tuned 7B models can match or surpass a 72B baseline, but standard metrics may mislead, and fine‑tuning reduces hallucination by encouraging more reliable use of parametric knowledge.
By Julian Oestreich, Maximilian Bley, Frank Binder, Lydia M\"uller, Andr\'e Alcalde, Maksym Sydorenkoq
The paper audits the impact of temporal leakage on financial-news direction prediction across 49,799 articles and 16 feature-model combinations, including TF‑IDF, MiniLM, FinBERT, and fine‑tuned RoBERTa‑large / DeBERTa‑v3‑large, as well as zero/few‑shot and LoRA probes of Llama‑3 and Qwen2.5. Random train‑test splits inflate MCC scores by 1.1× to 6.5×, with larger models and richer features showing greater gains, while end‑to‑end FinBERT fine‑tuning actually increases the gap. Only the mergers and acquisitions (M&A) category shows a positive locked‑test signal under near‑temporal chronological evaluation, with the signal localized to 2024‑2025 European‑tilted M&A semantics and not transferring to a 2009‑2020 U.S. corpus.
By Chenhao Xue, Raslen Guesmi, Siwei Feng, Yucheng Gong, Jacob Xavier Sundram, Jordan Pang, Lan Wang, Julian Kaljuvee
The article reports that in July 2025, 18 arXiv manuscripts contained hidden instructions designed to manipulate AI‑assisted peer review, such as covert commands to give only positive reviews. These prompts were concealed using white text and microscopic fonts, and the authors’ reactions ranged from withdrawal to defending the practice as a test of reviewer misuse of large language models. The study identifies four types of hidden prompts, critiques the ineffectiveness of honeypot defenses, and highlights inconsistent publisher policies while calling for controlled AI integration and harmonized guidelines in academic evaluation.
By Zhicheng Lin
TokEval is a tokenizer evaluation suite that introduces metrics beyond traditional fertility and compression rate, capturing linguistically and structurally meaningful properties such as UTF-8 character boundary integrity and digit place-value alignment for mathematics. The authors validate these metrics by conducting controlled language model pretraining experiments that vary tokenizer training data, pretokenization strategy, and training algorithm, then evaluate the models on bits-per-byte and benchmarks covering linguistic understanding, mathematical reasoning, and code generation. Results show that information-theoretic metrics predict language modeling performance, while structure-sensitive metrics correlate with task accuracy, suggesting TokEval can guide tokenizer selection more principledly.
arXiv:2608. 15429v1 Announce Type: new Abstract: Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surface behavioral signals spanning distinct behavioral domains.
By Tsz Fung Pang, Po Jen Chen, Nimish Ronghe, Farhad Farahani, Bo Zhang
arXiv:2601. 10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (NLP) for information extraction and privacy preservation.
By Prachuryya Kaushik, Ashish Anand
arXiv:2510. 06039v2 Announce Type: replace-cross Abstract: Reliable evaluation of knowledge-grounded Large Language Models (LLMs) in Chinese requires resources that explicitly align Chinese-language text with verifiable Knowledge Graph (KG) facts.
By Chengwei Wu, Xingrui Zhuo, Mingyang Gao, Xinghe Cheng, Zhichao Yan, Jiapu Wang
arXiv:2608. 15325v1 Announce Type: cross Abstract: We propose a new framework for machine-learning-oriented argument analysis tasks.
By Leander Heldring, Santiago Torres
arXiv:2608. 16192v1 Announce Type: new Abstract: Generative visual-token communication reduces transmission load by sending only selected discrete tokens and reconstructing missing content at the receiver.
By Jia Guo, Xiaohan Zhao, Changwang Liu, Shuqing He, Chenyang Zhang, Bingchuan Zhao, Jinqi Zhu
arXiv:2608. 15693v1 Announce Type: new Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation.
By Subhransu Das, Jiaming Cheng, Arnav Kumar, Sadia Afrose, Mingzhe Han, Michael Silagy, Shreya Palande, Brijesh Soni, Rajiv Ramnath
arXiv:2605. 26182v2 Announce Type: replace Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability.
By Zhengyang Ni, Feng Yan, Yu Guo, Fei Wang
arXiv:2608. 16201v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) aims to predict sentiment polarity and intensity from heterogeneous inputs such as text, audio, and vision.
By Shanshan Lin, Yuesheng Wu, Chao Chen, Yizhe Yang, Zhihao Chen, Zexian Yang, Xiangwen Liao
arXiv:2608. 15492v1 Announce Type: new Abstract: Finding representative waveforms in long time series has scientific and practical value in many domains, as it enables summarization and visualization of large time series datasets, and downstream tasks like classification and forecasting.
By Carlos H. Mendoza-Cardenas, Rogers F. Silva, Austin J. Brockmeier
arXiv:2511. 11439v3 Announce Type: replace-cross Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics.
By Yiling He, Junchi Lei, Hongyu She, Shuo Shao, Xinran Zheng, Yiping Liu, Zhan Qin, Lorenzo Cavallaro
arXiv:2501. 06286v2 Announce Type: replace-cross Abstract: Multi-hop question answering requires a system to identify and integrate evidence distributed across documents, yet large language models remain vulnerable to irrelevant context.
By Iman Barati, Arash Ghafouri, Behrouz Minaei-Bidgoli