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 55
When Agents Fail: Model or Harness--Who's to Blame?
LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior.Accordion: Elastic-Depth Inference via Fixed-Prefix Layer Looping
Large language models serve applications with diverse inference budgets, but training and maintaining separate models for each budget incurs substantial costs.The Punjabi Geet Toxicity Dataset (PGT-FG): Fine-Grained Multimodal Annotations for Toxic Content in Punjabi Songs
Resources for toxicity detection in Punjabi remain limited, particularly for musical content that combines linguistic and multimodal information.Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations
This paper examines speech characteristics of the Austrian National Council members (CMs).Principled Nonlinear Concept Erasure and Steering
Learned representations often encode sensitive attributes, such as gender or race, that may be undesirable or unsafe to retain.Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR
Adapting ASR to a domain with only untranscribed audio typically relies on pseudo-labeling, a strong teacher transcribes the audio and a student is fine-tuned on it.PHYRD: A Living Benchmark for Reproducing and Extending Theoretical Physics Research
Large language models and agents have shown significant power in advanced physical research.Residual Expert Routing for Text-Only Domain Adaptation of Factorized Transducer ASR
Fine-tuning the non-blank predictor of a factorized transducer on target-domain text improves recognition on that domain but degrades performance on the source domain.When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation
Quality-Aware Decoding (QAD) improves machine translation through test-time scaling, generating multiple candidate translations and selecting the final output with a quality-aware decoder.Natural Language Autoencoders Identify Without Explaining
Natural Language Autoencoders (NLAs) express a model's internal activations in the form of readable text.CounselPlex: A Stressor-Aware Full-Duplex Counseling Model
Full-duplex speech models can listen and speak at the same time, enabling natural, low-latency interaction.Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications
The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts.The Butterfly Defects: Tracing Cooperation in LLM Agent Networks
As large language models (LLMs) increasingly operate as interconnected agents, a fundamental question emerges: does individual cooperation translate into collective cooperation?ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents
LLM agents need long-term memory that can recover precise and mutually consistent evidence from growing interaction histories, particularly when answers depend on relations among facts rather than…On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
On-policy self-distillation enables post-training foundation models without relying on stronger external teachers.Every Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents
Hospitals regularly buy software that clinicians and patients depend on.ParaTaxe: a Suite of Tools for Processing and Publishing Multi-parallel Corpora
Over the past fifteen years, digital tools for parallelizing and aligning textual corpora have developed significantly within the field of digital humanities.Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules
We learn schedules for a continuous penalty relaxation of MAX-CUT by backpropagating through an unrolled classical solver.Frontier-OPD: Discovering the Edge of Agent Capability and Teaching Agents to Go Beyond
On-policy distillation aligns teacher feedback with a student's current behavior, yet acquiring useful supervision for multi-turn agents requires identifying both where guidance is needed and…KrishokTech: A Bengali Agricultural Advisory System with Explicit Authorization Controls
For agricultural advisory, generating an answer is only part of the problem: the system must also control unsafe requests, work with limited connectivity, and accommodate changing guidance.