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 86
Enhanced Masked Diffusion Unlearning
Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens with bidirectional context.System X: An LLM Decision Model That Replies from Its Own KV Cache
Decision models return probabilities over supplied options, but a deployed agent may also need to reply in words.Quality-Controlled Reply and Summary Data for Post-Training Small Language Models in AI Call-Screening Agents
Small language models have improved to the point where a phone can plausibly screen its own calls, answering on an absent owner's behalf without sending call content off the device, a…DiaLong: Benchmarking Reminiscence in Long-Context Dialogues
How well can transformer-based Large Language Models (LLMs) retain and recall memories in long contexts of dialogue?A failure of Imagination: VLMs fail to use visual representations for text, but self-distillation can help
Vision-language (VL) models are typically built by fine-tuning a language model to attend to visual features in service of a Visual Question-Answering objective.Self-Distillation for Supervised Fine-Tuning
Supervised fine-tuning treats the expert demonstration or gold response as a one-hot target, suppressing valid alternative continuations that the model would otherwise assign probability to.From Seeing to Reporting: A Theory of Reliable Visual Set Generation in Vision-Language Models
Vision-language models (VLMs) are asked to report what they see: to count objects, box them, parse a screen or pick a click target (GUI grounding).Where Are Language-Specific Features Represented in Multilingual LLMs? Everywhere
Previous work has argued that multilingual LLMs encode language-specific features most strongly in their initial and final layers, implying that intermediate layers support language-agnostic…ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changing energy cost of inference…Auditing Tool Traces in Agentic LLMs: Source Localization and Counterfactual Dependence Testing
Agentic LLMs increasingly support scientific prediction by grounding decisions in external evidence.EmotiQ: A Quantum Residual Specialist Framework for Text Emotion Classification
Emotion classification from text is challenging because many affective states are distinguished by subtle linguistic signals and semantically overlapping boundaries.Narrow Decision Models: A System-1 Architecture for Calibrated, Typed Decisions
System One models, introduced with TypeSafe's Jev, answer typed questions about a state with calibrated probabilities instead of generated text: choosing among options described in natural language…Flattening Fantasies: Analyzing Stereotypes in Pornographic Discourse
This study presents a large-scale quantitative analysis of 5.4 million video titles from xHamster, the world's fourth most visited pornography platform, to examine linguistic patterns used to…Representations in Motion: Layer-wise Rotation and Trajectory Divergence in LLMs
Recent work suggests that activation dynamics--how representations change during inference--might be more revealing about language model behavior than static readouts from individual layers.Assertion and Belief: Moore's Paradox in Language Models
Moore's paradox \citep{moore1942} concerns sentences such as ``It is raining, but I don't believe that it is,'' which may well be true yet cannot be sensibly asserted.The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering
Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it…A Multi-granularity Interaction Network for Relational Triple Extraction
Relational triple extraction identifies entity relations from raw sentences without depending on entity type information.LAMB: Latent Multi-Hypothesis Beliefs for Long-Horizon Large Language Agents
Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states.Dynamic System Inspired Continuous Large Language Model for AI4Science Tasks
Scientific foundation models increasingly operate on continuous phenomena, yet still use discrete residual computation.Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness
In this paper, we investigate the issue of difference awareness in LLMs, defined as a model's ability to recognize and acknowledge meaningful differences between social groups in fairness…