AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 18 September 2026 to 6 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 213
GeoOutageBench: Benchmarking Ambiguity-aware, Ontology-grounded Geospatiotemporal KGQA for Multimodal Power Outage and Resilience Analysis
We introduce GeoOutageBench, a benchmark for assessing LLM-based geospatiotemporal KGQA for multimodal outage and resilience analysis.PADMÉ: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators
Language models are frequently employed to evaluate other language models.Better Behavioral Prediction, More Faithful Model Ablations? Evidence from Sequential Choice
Using predictive models to explain cognition requires more than accurate behavioral predictions.A Character-Level Neural Approach to Sinhala Sandhi Splitting
Sinhala Sandhi splitting recovers the constituent words or morphemes hidden inside a phonologically merged surface form.When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarification, answering directly, or declining.Language Models Are "Insecure" Reporters
As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outputs of models becomes more difficult.Principled Thoughts for Latent Recursive LLM Systems
Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supervises only the…Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning
Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents.Concept Direction Reliability Across Languages with Different Tokenizer Fertility
Extracted sentiment directions can vary across samples even when downstream sentiment classification remains accurate.SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety
Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under benign instructions and environments.FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models
Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time.Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering
We study how Gemma 4 31B represents African languages and responds to cultural steering.The Canonical Order Problem: When Large Language Models Are Unreliable Knowledge Bases for Multi-Valued Relations
Large language models (LLMs) are increasingly used as knowledge bases (KBs) due to the vast amount of knowledge they acquire during pre-training.Lost in Translation: Measuring the Effect of Non-Native English on End User Performance of Large Language Models
Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematically lower-quality responses than fluent…CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles
Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remains comparatively underexplored despite requiring…Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
Large language models (LLMs) can predict human brain activity across a variety of brain regions during natural language comprehension.Learning from Teacher Continuations at Student States
We present OLIVE (OnLine InterVEntion).Population Fidelity: Evaluating Population Representativeness in LLMs
Large language models (LLMs) show considerable potential in simulating human attitudes and preferences.OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perform safely online.In-Context Learning Amplifies a Latent Symbolic Circuit
Large language models can learn abstract rules from just a few in-context examples, but how their internal mechanisms activate as examples accumulate is not well understood.