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 241
A retrospective analysis on the use of LLMs to study infant syntax learning
Large language models (LLMs) have increasingly been used to investigate how children acquire syntax at an early stage of development.Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment.Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction.PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation
Procedural character generation aims to populate games, simulations, and other virtual worlds with diverse characters.Knowledge Pull Requests for Continual Document Authoring
We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable.Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden.Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding
Autoregressive OCR vision-language models accurately convert document images into text and structured markup, but require one sequential decoding step per output token, limiting inference speed.Discovery-Driven Integration of Disjoint Tables via Text
Integrating heterogeneous datasets within data lakes is a critical challenge, particularly for semantically related tables that lack the explicit attributes needed to be joined.Detecting GPT-Assisted Writing Using Interpretable Stylometric Features
Distinguishing GPT-assisted from independently authored student writing has become a critical challenge in academia.Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action.Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independent solutions and…SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns…Agensh: Scaling Organizational Intelligence to 1,024 Agents
A multi-agent system can reduce latency on complex tasks by executing work concurrently.Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabling non-autoregressive text generation.Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification
Memes often derive their harmful, hateful, or sarcastic meaning from small but decisive visual, textual, or cross-modal cues.COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs.Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation
Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow.Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone.Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms
Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem.Classifying Interpretive Canons at the Sentence Level: A Benchmark from the German Federal Constitutional Court
Judicial reasoning remains challenging for large language models (LLMs) to analyze.