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 21
Detailed Derivation of The Backpropagation Algorithm
Backpropagation is the standard method for computing the gradients that train neural networks, but it is usually presented in a compact vector form that skips the intermediate steps.Multi-Agent Collusion and the J-Space
LLM agents are increasingly deployed in Multi-Agent Systems (MAS), and they introduce the risk of coordination among agents that might escape human oversight.Decision Models as Policy Gates for Coding Agents: Explicit Policy Boundaries Improve Detection and Reduce False Alarms
Coding agents can destroy data, leak secrets and message the wrong person faster than a human can review.Test-Time Scaling for Open-Ended Reasoning at Small Model Scale
A vote over a model's samples can only help when the samples disagree.Who Should Score the Cache? Mid-Depth Layers Are the Best Judges of KV-Cache Eviction
Key-value (KV) cache eviction methods rank tokens by attention scores, and each layer scores its own cache.Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories
AI reviewers are increasingly used to assess scientific manuscripts, yet it remains unclear whether their judgments reflect the improvements authors make through revision.Metamorphic Testing for Evaluating Robustness of Sentiment Analysis Models
Machine learning systems are challenging to test using traditional software testing methods because their behavior is learned from data rather than explicitly programmed.Hinted Scaling Laws
Scaling laws predict the outcome of large, expensive training runs by extrapolating trends from smaller, cheaper runs.Current state of LLMs for Arabic dialectal machine translation
This work presents an evaluation of large language models (LLMs) for English to dialectal Arabic machine translation on the MADAR dataset.When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency
Large language models (LLMs) are increasingly used to annotate text for social science research, content moderation, and training data.Concise-9B: Removing the Slack from a Reasoning Model's Thinking
Reasoning models answer better when they think longer, but a thinking trace keeps going well after its answer has formed.Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs
We propose a methodology for investigating the differences between natural and synthetic language in a challenging setting: humorous improvisational dialogue.Swap, Replicate, Read the Mass: A Protocol for Auditing Demographic Bias in System One Decision Models
System One decision models replace text generation with typed, probability-scored answers and are entering production.Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics
LLMs are increasingly used to design heuristics for computer systems.AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents?
Large language models (LLMs) are increasingly used in dynamic financial trading, yet real-time trading benchmarks mainly evaluate agents by cumulative returns and risk-adjusted performance.Agentic Context Management for Multi-Turn Human-AI Conversations
LLMs degrade in multi-turn conversation partly because of context pollution: the model's own earlier outputs stay in context and anchor later turns, so an early misreading of the user's intent can…WeSearch: A Unified Model-Centric Retrieval Framework for WeChat Search
We present WeSearch, a unified, model-centric retrieval framework for large-scale, continuously evolving content search.Dual-Axis Policy Entailment: A Benchmark for Policy-Change Reasoning
Whether a policy shifts domains and, by extension, continues, broadens, narrows, or reverses previous policy is of paramount importance to the study of public policy.Skill++: Towards Lifelong Agents via Routing-Aware Skill Refinement
Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body.Distinguishing among reasoning levels of GPT 5.5 Pro via a grammar lens benchmark
Does the level of test-time processing effort affect a language model's computational capability?