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 92
Explaining Chess and Go in Natural Language
Modern chess engines play far beyond human ability, often choosing moves whose underlying ideas are difficult for humans to understand.Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making
Many language-based applications require probabilities over a finite set of decisions rather than open-ended responses.Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling
Recent speech brain-computer interfaces (BCIs) increasingly rely on large models and complex multi-stage pipelines for neural decoding.Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models.What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space
Detecting faithfulness hallucinations in large language models (LLMs) is crucial for their safe deployment in high-stakes domains.AMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated Critics
Text detoxification requires balancing toxicity removal, semantic preservation, and fluency.MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai
Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors.ReLaDrift: Recurrent Language Generation via Drifting for Test-Time Scaling
Drifting Models generate a sample with a single function evaluation, making them attractive for fast parallel language generation, but their one-step formulation does not support iterative refinement.MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out.MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused.Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context
Reasoning systems increasingly improve answers by incorporating additional context into the model's input, from multi-agent debate, where agents read their peers' responses, to self-refinement…Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages
Small-to-large language model routing can reduce inference cost by escalating difficult inputs while retaining easier ones on a smaller model.Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls.Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers
A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier prefers.Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To
Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversight.Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection
Current Chain-of-Thought (CoT) verification methods detect reasoning faithfulness from model outputs or static activations, but are limited in explaining how unfaithfulness develops during generation.Annotrace: A Workbench for Step-Level Annotation of Agent Traces
Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool.SimOPD: Relational Knowledge Transfer for On-Policy Distillation
A key challenge in on-policy distillation (OPD) is extracting effective supervision from teacher knowledge.Inferring L1 Backgrounds from L2 English with LLM Token Probabilities
Native language identification (NLI) infers a non-native speaker's first language (L1) from their second language (L2) production.Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints.