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 17 September 2026 to 5 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 45
The Voice on the Line
A transcriber listening through one microphone also hears everyone near it.Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers.CRIM: Composable and Reusable Item Memory for Efficient Personalized Retrieval
Large language models incur substantial training and inference costs in personalized search and recommendation, as growing interaction histories lengthen request inputs and repeatedly expose the…Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning.Agreement Between Reconstructed and Native GDELT GKG Records: A Field-Level Baseline
The Global Knowledge Graph (GKG) of the Global Database of Events, Language, and Tone (GDELT) characterizes news articles using named entities, topics, quantitative and temporal features…The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning
We measure the emotion geometry of six LLMs spanning Google's Gemma 2 family.ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation
Text-in-image translation aims to translate all textual content embedded in an image.INVAR-Agri: Detecting Discrepancies in Multilingual Operator Manuals of Agricultural Implements with a Fine-Tuned LLM
Operator manuals of agricultural implements are delivered in many languages, and the standards require that competent persons review every translation, which makes this review the bottleneck.Probing the phon* representations of the Mimi codebooks
Neural audio codecs are increasingly used to encode speech for integration with large language models.Skill$^{\infty}$: Recursive Self-Improvement for Agent Skill Optimization
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI.A Contextual Measure of Ambiguity in Prescriptive Text
Ambiguity in prescriptive text such as laws, contracts, rules, policies, or recommendations can be both desirable (e.g., if it enables a law to adapt to changing context, such as new technologies)…MANTIS: Multi-Axis News Transformations for Instance-Wise Stress Testing and Worst-Case Training in Fake News Detection
Automated fake news detection is vital on social media, where fake news is easily rewritten to fool detectors.GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
Multi-reward reinforcement learning offers a promising framework for aligning large language models (LLMs) with diverse objectives, but conflicting reward signals can induce ambiguous update…Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation
Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making translation challenging.MATCHA: A Chinese Multi-Disorder Mental Health Dataset with Cross-Lingual Analyses on Social Media
Mental health research on social media has been dominated by English-language datasets and DSM-5-centered resources, limiting cross-lingual and cross-cultural understanding of online mental health…S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-thought (CoT) reasoning, avoiding difficult and costly critic training.An Algorithmic Account of Few-Shot Concept Induction in Language Models
Both models and minds not only encode features that describe an entity, but can specifically represent which features of that entity are relevant for a given context.StateLoop: Persistent State for Looped Transformers
Looped Transformers offer a parameter-efficient approach to language modeling by repeatedly applying a shared backbone.LoopFold: Parallelizing Recurrent Depth in Looped Transformers
Looped Transformers increase computation per token by repeatedly applying a shared backbone, offering a way to improve language modeling and downstream task performance at a fixed backbone parameter…EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering
Language models are increasingly considered for clinical decision support, where their answers should be grounded in clinical evidence and remain robust to irrelevant information.