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 5
Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees
Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value.Autonomous agents for electricity-system planning
Planning electricity systems requires repeated decisions that connect regional resources, investment, operation and network constraints.Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models
Reasoning models allocate test-time compute across distinct behaviors such as planning, deriving, and verifying.Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory even though only a few experts are activated per token…Robots in the City: Persona-Based Perceptions of Urban Robots
Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a street remains unclear.On the Design of Hyper-Connections: Simplification, Stability, and Scalability
Hyper-Connections (HC) architectures are increasingly adopted in frontier language models, yet their components remain insufficiently understood and introduce non-negligible training overhead.How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition
Activation steering can modify language-model behavior without parameter updates, but behavioral efficacy alone does not determine whether an intervention is usable.Familiar letters, not related languages, let unseen languages into a shared space of meaning
Hundreds of languages have written text but almost no translations, and whether a model learning one from untranslated text builds on a related language or familiar letters is unclear: they usually…Holistic Parallel Supervision for Expressive Speech to Speech Translation
Expressiveness is central to speech-to-speech translation (S2ST), yet existing datasets rarely align source and target speech jointly in content, prosody, timing, and speaker identity.Who Pays for the Knowledge Models Copy? Model Collapse as Rogers' Paradox
Generative models trained on the output of earlier models lose knowledge across generations, rare knowledge first.When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models
When a language model chooses a number between 1 and 30, every integer in the range is valid, yet the model can favor particular answers.Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears.SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation
Text-to-SVG systems are commonly evaluated by applying raster-image metrics to rasterised outputs, yet whether these scores capture fine-grained prompt faithfulness remains unclear.Adapting Qwen3 to Tajik from 0.6B to 8B: Lower Text Loss Did Not Mean Better Understanding
Small LoRA adapters trained on Tajik news and books lowered Qwen3's Tajik text loss at every size we tried, from 0.6B to 8B, by 0.60 to 1.45 nats per token, but none of them improved Tajik reading…ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction
In natural human-AI dialogue, users' corrections, requests, and self-descriptions carry reusable signals about how they want work to be done.Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers
This paper presents an overview of \emph{SciClaimEval}, a pilot task at NTCIR-19 on verifying scientific claims against the tables and figures of the papers in which they appear.Reconciling Privacy with Provenance for Language Model Watermarks
Watermarking has great potential for regulating the use of language models (LMs), but its deployment has been marred by controversy, as many users argue that fine-grained tracking of LM usage…The Harness Is the Model: Agent Scaffolding Changes a Fixed LLM's Compliance with Banking Conduct Rules, Unevenly Across Models
Banks validate language models, but they deploy systems: a model inside a harness that decides what it sees, which tools it can call and who checks its actions.Growing One's AI Tools: A Paradigm of Practice-Grown Tools
Professionals have long used software built for them by others.Accelerating Long-Context Decoding in Large-Scale Hybrid LLMs Without Retraining
The full-attention layers of large language models (LLMs) make every generated token more expensive than the previous one, slowing models down on long-context tasks.