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 247
Error-Supervised Synthetic Learner Writing for Automated Essay Scoring
Synthetic essays can help reduce dependence on human-written data in Automated Essay Scoring (AES).ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders
Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output.Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization
Sink-aware deployment may identify important first-token attention heads before a model is quantized, then reuse that map at the edge.On the Efficiency-Safety Dilemma in Large Reasoning Models
Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning.Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing
End-to-end document parsers increasingly offer an optional reasoning mode for complex pages.Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans.Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations
E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent.Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories.Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions
Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether…STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification
Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable.GRACE: Grounded Adversarial Reasoning over Canadian Law
Large language models have shown strong performance across a range of legal tasks, but existing benchmarks rarely evaluate the ability to take and defend a legal position, reason under incomplete…Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, function calling, data extraction), yet little is…FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model
While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit assignment crisis and waste…Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking
We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM architectures on the Multilingual LibriSpeech dataset.From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters
Disaster-risk-reduction archives describe hazard events in prose that databases such as EM-DAT (Delforge et al., 2025) cannot ingest directly.Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval
Temporal Information Retrieval (TIR) has been increasingly critical given the rise of Retrieval-Augmented Generation (RAG).this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent
Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person.Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
Large language models (LLMs) drift out of date the moment their pretraining ends, yet retraining from scratch is prohibitively expensive.Measuring the Assistant's Harmlessness Preferences on the User Turn
Post-training turns a general next-token predictor into a chat model with a persistent assistant persona.XYEval: Agents say yes to bad advice
Effective communication between users and AI agents is essential for human-AI collaboration.