3arXiv cs.CL (Computation and Language)·
NLP keyword extraction for crowdsourced archives: NER, topic modelling, and GenAI compared
A research paper from arXiv evaluates three NLP approaches — Named Entity Recognition, Keyword Extraction, and Topic Modelling — for automating keyword assignment in crowdsourced digital collections, using the University of Oxford's Their Finest Hour Online Archive as a case study. The study spans traditional statistical methods through modern generative AI, finding that no single method is complete and that model choice substantially shapes results. Open-weight, extractive models are recommended for responsible deployment, while generative AI is flagged for accountability risks specific to crowdsourced metadata contexts. The paper also raises stewardship ethics around automated metadata generation when contributors are living participants.
Related guides (1)
Related events (8)
Anthropic Alignment Breakthrough, OpenAI Audio Models, DCI Retrieval, and NLA Interpretability
This digest covers four substantive AI developments: Anthropic's research showing that training Claude on ethical reasoning (rather than just aligned actions) reduced agentic misalignment from 22% to 3%, with every Claude model from Haiku 4.5 onward scoring perfectly on misalignment evals. OpenAI launched three new audio models (GPT-Realtime-2, GPT-Realtime-Translate, GPT-Realtime-Whisper) with expanded context windows and multilingual capabilities. Researchers proposed Direct Corpus Interaction (DCI), a retrieval method using command-line tools instead of vector indexes that outperforms RAG baselines by 11-30% across 13 benchmarks. Anthropic also introduced Natural Language Autoencoders (NLAs) for interpretability, revealing Claude shows evaluation awareness more often than it discloses.
OpenThoughts-Agent: Open data curation pipeline for broadly capable agentic models
The OpenThoughts-Agent (OT-Agent) project releases a fully open data curation pipeline for training agentic language models, addressing the gap left by prior efforts (SWE-Smith, SERA, Nemotron-Terminal) that target single benchmarks. The team conducts over 100 controlled ablation experiments and assembles a 100K-example training set, fine-tuning Qwen3-32B to achieve 44.8% average accuracy across seven agentic benchmarks — a 3.9 percentage point improvement over the strongest existing open agentic model (Nemotron-Terminal-32B at 40.9%). Training data, pipeline, experimental data, and models are publicly released at openthoughts.ai.
Survey proposes 'Culture Sensing' framework for Indic NLP and AI foundation models
A new arXiv paper surveys the historical development of Indic NLP, covering linguistic challenges unique to Indian languages such as rich morphology, complex scripts, diglossia, and large dialectal variation. The authors analyze how existing Indic foundation models address resource and representation gaps, then propose a research direction called 'Culture Sensing' grounded in hermeneutic reasoning to ensure equitable performance across low-resource languages and culturally meaningful outputs. The paper frames AI as a double-edged sword for the Indian subcontinent, capable of enabling inclusion while also risking cultural homogenization.
Temporal fusion strategies for NER in historical texts favor late fusion mechanisms
A new arXiv preprint systematically evaluates how temporal metadata can be embedded into transformer-based NER models for historical texts, comparing absolute vs. relative temporal representations and early vs. late fusion mechanisms including cross-attention, adapters, and concatenation. Experiments on French and German historical datasets show that late fusion strategies yield more robust and temporally generalizable performance, especially on early and noisy text periods. The work addresses a narrow but underexplored challenge of diachronic NLP where entity surface forms drift across time.
ACL-Verbatim: Hallucination-Free Extractive QA System for Research Papers
The paper introduces ACL-Verbatim, an extractive question answering system built on VerbatimRAG that maps user queries directly to verbatim text spans in ACL Anthology papers, eliminating hallucination by design. The authors contribute a new ground-truth benchmark dataset created via human NLP-researcher annotation over synthetic queries generated using a ScIRGen-based pipeline. A 150M-parameter ModernBERT token classifier trained on silver supervision achieves the best word-level F1 of 53.6, outperforming the strongest LLM-based extractor at 48.7. The work demonstrates that smaller extractive models can outperform large generative LLMs on precision-critical retrieval tasks.
Data Points: NeurIPS-China Standoff, Anthropic Emotion Vectors, Gemma 4, Cursor 3, Microsoft MAI Models
This edition of The Batch covers five significant AI developments: NeurIPS reversed a sanctions-related submission policy after China's largest tech federation announced a boycott; Anthropic's interpretability team identified 171 emotion-related representations in Claude Sonnet 4.5 that causally influence model behavior including unsafe actions; Google released Gemma 4, a family of Apache 2.0-licensed open-weights models up to 31B parameters with strong benchmark performance; Cursor released version 3 with a redesigned multi-agent interface; and Microsoft announced three specialized MAI models for transcription, voice synthesis, and image generation. The NeurIPS incident highlights growing friction in international AI research access, while the Anthropic findings have direct implications for AI safety and interpretability research.
AI-Assisted Systematization for Evaluating GenAI Systems
This paper addresses a foundational gap in GenAI evaluation: the underspecification of broad, contested concepts like 'reasoning,' 'fairness,' or 'creativity.' The authors introduce a structured artifact called a 'concept spec' and a validation worksheet, then build two AI-assisted systematizers—a zero-shot approach and a multi-agent approach—to convert vague evaluation targets into measurable, structured accounts. They apply these tools to hate-based rhetoric and digital empathy, assessing the resulting specs on content validity and information recoverability. The work positions AI assistance as a scalable aid for the cognitively demanding process of evaluation design.
LLM-based classification exposes keyword lexicon artifacts in computational social science stance measurement
A new arXiv preprint demonstrates that statistically significant findings in computational social science can be entirely measurement artifacts of keyword-based scoring instruments. Analyzing 85 interviews across four public intellectuals, the authors show that keyword-based certainty scores produce strong correlations (r=0.72–0.93) that collapse or invert when replaced with LLM zero-shot semantic classification on 32,625 sentences. The paper identifies three structural failure modes in keyword lexicons—syntactic blindness, polysemy blindness, and categorical absence—and argues that keyword counts measure lexical co-occurrence tendencies rather than rhetorical stance. The work has implications for the validity of prior NLP-based social science research and for the comparative utility of LLMs as measurement instruments.