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 18 September 2026 to 6 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 205
Steering Language Model Goals with Value Transplant
Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes.Counterexamples to Local Reconstruction Gain as a Proxy for Final Fidelity in Residual Completion
Residual completion augments query-aware sparse attention by estimating the contribution of tokens omitted from the exact sparse computation.Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models
Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people.Evaluating Machine Unlearning in ASR
Machine unlearning (MU) offers a path to compliance with "right to be forgotten" regulations.Unknown is not normal: separating language-model extraction from rule-based decision logic for clinical risk scores
Large language models (LLMs) are increasingly used to compute clinical risk scores from free-text notes.Understanding Clinical Cognitive Dialogues Using Large Language Models
In-person cognitive assessment is both a test and an interaction.Training and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive Reduction
This monograph develops a unified account of training and inference in Power Law Decoder Representation language models (PLDR-LLMs).Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems
With the advent of word representations, word similarity tasks are becoming increasing popular as an evaluation metric for the quality of the representations.Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch
Among closely related North Germanic languages, the quantification of language distance has traditionally relied on qualitative methods, lacking a unified multi-dimensional computational framework.Toward a Graded Measure of Belief Stability in Large Language Models
Large language models (LLMs) increasingly mediate how people access and reason with information, yet factual reliability is usually evaluated one judgment at a time.RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints
Retrieval-augmented generation systems are extensively instrumented with metrics, benchmarks, traces, and automated judges, but these tools do not decide whether a proposed policy change is safe to…LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks
The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they cannot move beyond statistical pattern matching into…PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models
Figural divergent thinking is the ability to develop a given shape fragment into an original drawing.X-MoD: Practical Scaling Laws for Sparse-Depth Routing Beyond Mixture-of-Depths
Mixture-of-Depths (MoD) enables conditional computation across Transformer depth by routing only a subset of tokens through selected layers, but its original one-sparse--one-dense alternation…Explainable and Generalisable LLM-based Cognitive Decline Detection with Spontaneous Speech
Alzheimer's disease (AD) and mild cognitive impairment (MCI), which may precede AD, manifest early through subtle linguistic and acoustic alterations.Loop Dropout: Regularizing Shared Updates in Looped Language Models
Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block.USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents
On-policy distillation instils multi-turn agentic reasoning through dense token-level supervision on the student's own trajectories, but a single domain saturates early, so further supervision has…When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough?MAS-OPD: On-Policy Distillation for Multi-agent Systems
Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone.Coherence-Aware Distributional Evaluation of Open-Ended Text Generation
Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, yet can miss fundamental dimensions of quality.