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 57
Preference Optimization Improves Definition Generation: Semantic Change in EU Institutional Sustainable Finance Disclosures
Dictionary-like definition generators are known to be useful for lexical semantic change detection (LSCD).Distill, Debate, Discover: Grounding Multi-Agent Research Ideation in Graph-Distilled Insights
Large language models (LLMs) are increasingly used to support research idea generation and scientific discovery.How Does Post-Training Shape LLM Value Preferences?
During post-training, large language models (LLMs) learn value preferences from corpora that may contain imbalanced proportions of opinions associated with different demographic groups.Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards.TT-SAX: A Two-Track Time Series Symbolization for Natural Language Shape Querying
Natural language querying for time series databases aims to let users find what they need in long histories of data by asking in plain language.The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts
Hybrid retrieval, which fuses a sparse lexical retriever with a dense neural one, is widely recommended in the software documentation surveyed in September 2026, usually with reciprocal rank fusion…What the Specification Did Not Say: Specification-Oracle Gaps in Test-Graded Coding-Agent Benchmarks
Coding-agent benchmarks often describe a task in natural language but grade it with tests taken from the upstream project.Group Relative Policy Optimisation Improves Multilingual Speech Recognition in Low-Resource Languages
Autoregressive encoder-decoder speech recognition models trained with teacher forcing can suffer from exposure bias, limiting their ability to recover from their own prediction errors at inference…Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG
Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding.Spectral Smoothing and Spiking Perturbations Reconfigure Capability Profiles and Selective Task Performance in Large Language Models
Singular-value spectra encode important structure in transformer feed-forward projections, yet their causal role in downstream behavior remains underexplored.WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias
Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture.Scaling Laws for Safety Probes
Safety probes trained on a model's activations are a standard tool for monitoring language models in real time.Direct cueing of word identity through word duration: evidence from Mandarin homophones
While there is increasing evidence that words are stored in the mental lexicon with some phonetic detail, there are open questions about exactly which phonetic details are stored and whether they…From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots
Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain.Disentangling Robustness and Sycophancy in Multilingual LLMs
When a multilingual LLM agrees with a user's false premise, is it being sycophantic, or does it simply not know better in that language?ULME: Predictive Coupling for Mutually Reinforcing Embedding and Language Modeling
Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a…Meaning Contracts: Local Semantic Geometry in Large Language Models
This paper studies the local geometry of semantic meaning in large language models.UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization
Guardrail models are increasingly used as safety layers for LLMs and agentic systems, but most are trained on fixed prompt or response interfaces and become unreliable when the same safety case…How Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models
Can a small change in wording move an AI model from refusing a sensitive request to acting on it?Abstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses
AI assistants built on large language models (LLMs) are trained on human feedback and increasingly personalized to users' stated preferences.