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 88
Axiomatic World Modeling for Physics Reasoning
Recent research-level physics-reasoning benchmarks for LLMs reveal a failure mode that lies not in knowledge or execution, but in modeling the world being reasoned about.EGIP: An Evidence-Grounded Interaction Protocol for Clinical Agents
Interactive clinical agents acquire evidence through patient dialogue and diagnostic examinations, yet their performance also depends on how the interaction environment exposes information…From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception.ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch.Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms…Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs
The safety capabilities of large language models (LLMs) are highly uneven across different languages, often allowing cross-lingual attacks to bypass safety guardrails.Muse Glimmer 30B: An On-Device Agentic Model
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware.What RL Brings to Reasoning: A Few Decisions the Base Model Would Not Make
Reinforcement learning with verifiable rewards (RLVR) substantially improves mathematical reasoning, but what it adds to the base model remains unclear.Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval
Explicit memory systems transform conversation history into persistent representations intended to improve future access, often at substantial construction cost.Verifying Human-Written Reasoning References
Evaluating the reasoning of AI systems often relies on human-written reasoning chains as references, yet the logical support for their individual steps is rarely verified.When Do Repetition Loops Lock? Truncation Sampling, Bounded Penalties, and a Blind Spot in DRY
Language models sometimes repeat verbatim until the generation limit.DiffuPlan: Editable Planning State for Diffusion Language Model Agents
Diffusion language models (dLLMs) are emerging as an alternative to autoregressive (AR) language models, yet dLLM agents largely inherit an interaction protocol designed for AR generation: once…Neuro-Inspired Inhibitory Message Passing for Accurate and Token-Efficient Multi-Agent Reasoning
Multi-agent systems promise to solve problems by bringing together information beyond the reach of any individual agent.PV-Decoding: Progressive Verification Decoding with Decode Gating for Diffusion Language Models
Discrete diffusion language models (dLLMs) offer an attractive alternative to autoregressive generation by updating multiple tokens in parallel, but their inference efficiency is still limited by…GLOSS-MT: Controllable Low-Resource Machine Translation with an Editable Dictionary
Adapting a pretrained machine translation (MT) model to new terminology usually requires new parallel data and another round of fine-tuning, which is costly for low-resource languages.BanglaBBQ: A Bias Benchmark for Question Answering in the Bangladeshi Context
This paper introduces BanglaBBQ, a question-answering bias benchmark designed to capture stereotypes grounded in the Bangladeshi context, in both Bangla and English.ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction
Existing Multi-token prediction (MTP) methods are auxiliary by design: the multi-horizon loss mostly trains modules attached to the backbone, and each added horizon costs another module and another…Information Theory of Random Composition Trees
Random composition trees model the hierarchical semantic structures of meaningful texts as a statistical ensemble generated by recursively splitting texts into coherent chunks.Who Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models
Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it.Table Serialization Determines Which Relations Language Models Preserve
We study how text serialization affects table lookup in instruction-tuned language models.