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 154
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens.A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic
Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models.Structured but Silent: Probing Capability Requirements in LLM Hidden States
Reliable tool use requires more than triggering a mechanism or matching a query to an API description.The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed.Are Language Models Script-Aware?
Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation.DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own.Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training
Automatic assessment of communication quality in dyadic counseling conversations is bottlenecked by data: expert-rated corpora are small and expensive to grow.HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM).Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents
LLM tool-use agents operate in dynamic environments where many actions carry operational risk.DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs
Speech-LLMs often exhibit prompt overfitting, where models solely trained on automatic speech recognition (ASR) instruction fail to generalize to new instructions such as speech translation and…SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis
Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated training data.Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
Natural-language access to RDF knowledge graphs is a core Semantic Web ambition.Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
Full-duplex spoken dialogue models listen and speak at the same time, enabling voice agents to have natural, low-latency interactions that turn-based systems cannot offer.Penalty-Framed No-Valid-Option MCQA: Analyzing LLM Abstention under Invalid Choices
Multiple-choice question answering (MCQA) is commonly used to evaluate large language models under the assumption that one of the provided options is correct, typically using answer-selection…Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation
COMET reports translation quality as a single number, and that number is routinely compared across target languages written in different scripts.Symphony for Text Generation: Benchmarking Clinical Note Generation
Ambient documentation systems are rapidly gaining adoption, yet their impact on clinical note quality remains poorly characterized.The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception
Fine-grained emotion recognition supports therapy tools and social robots, but it needs facial data, which raises privacy and data-protection concerns.Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-$r$ adapter beside each frozen quantized weight…STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty
We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependency resolution.