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 210
SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys
Large Language Models (LLMs) offer a scalable way to simulate survey respondents using demographic profiles and observed reference responses.Rubric-Aware On-Policy Self-Distillation for LLM Personalization
LLM personalization aims to generate responses aligned with individual users' preferences and needs.When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models
Despite substantial progress across downstream applications, vision-language models (VLMs) remain susceptible to language bias, often prioritizing linguistic cues over visual evidence and…Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
Multi-agent large language model (LLM) debate is often evaluated by whether final answers improve, but movement is not necessarily improvement: the same discussion can rescue an initially wrong…EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning
Recent work has explored improving agents by jointly evolving their harnesses and models, but often takes a ''potpourri'' approach that bundles together new tools, new decision-making procedures…Decide, Don't Generate: Competitive Dimensional ABSA with Jev's Typed Decisions
Aspect-based sentiment analysis (ABSA) has largely turned to text generation.Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation
Large language models process conversation history as unverified context: false premises injected into prior turns can be adopted as fact, a failure mode we term session-level contamination.MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs
Large Language Models (LLMs) perform well on reasoning benchmarks, but it remains unclear whether this reflects genuine contextual reasoning or reliance on facts memorized in their parameters.Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence.Do Coding Agents Reuse Existing Code or Reinvent the Wheel?
Coding agents are increasingly deployed for iterative development on real repositories, yet existing evaluation barely answers a basic question: \emph{do coding agents reuse existing code or…From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features
Sparse autoencoders (SAEs) are an important tool for mechanistic interpretability, but interpreting their many features remains challenging.Deep Learning Methods in Neuroscience: From Modeling Molecular Mechanisms to Classifying States of Consciousness
A critical analysis of contemporary approaches to the study of conscious states.How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?
While recent studies have explored human behavior and preference simulation using large language models (LLMs), it remains unclear how well LLMs can simulate subjective evaluations from real…Multilinguality in Hybrid Attention LLMs
In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs combine multiple variants of attention to mitigate the quadratic complexity of…TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration
Reliable confidence estimation is essential for large language model deployment.AwarenessBench: Assessing Cognitive Capabilities of Language Models
As language models (LMs) exhibit increasingly consciousness-like behaviors, evaluating their cognitive abilities becomes essential.Self-Adapting Group of Experts for Multi-Agent Reasoning
Multi-agent systems bring together language model agents with different roles to propose, review, and refine solutions.Semantic Prefix Oracles for LLM Decoding: Contracts and Differential Validation
Constrained decoding can enforce regular or context-free output formats, but many program-generation failures are semantic: scope, typing, and declaration effects depend on context.Frontier Learning: Training LLM Reasoners at the Edge of Capability
Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities.LLMs are General Asynchronous Agents
Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat.