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 187
Training LLM Judges from Language Feedback via Position-Selective Self-Distillation
We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them.Recovering Off-Policy Supervision for Speculative Decoding
Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy token invalidates supervision for all subsequent slots in a block.Evaluating Persistent Calibration under Evolving Model Knowledge
As AI systems move from static repositories to agents that are capable of continual adaptation and learning, maintaining their trustworthiness means equipping the models backing them with the…Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?
Understanding multi-perspective alternative narratives requires identifying how their information agrees, conflicts, or differs across sources.Uncovering Uncontrolled Repetition through Residual Stream Dynamics
Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks.Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems
Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global constraints.StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning
Large language models deployed as personalized assistants must reason over long, evolving interaction histories.Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification
Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments.You're Hired: Strategic Model Selection for LLM Collaboration
While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems remain bottlenecked on pre-defined and…When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning
Large reasoning models (LRMs) improve performance on complex tasks through extended reasoning, yet the same process can degenerate into redundant verification and persistent generation loops.Whose Voice Survives the Summary? A Voice-Retention Audit of LLM Employee Listening
Organizations increasingly route employee feedback to leaders through large language model (LLM) summaries, an unaudited layer that silences already-spoken voice.BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic Dialects
With the rapid growth of Arabic NLP, several models, datasets and benchmarks have been reported.Forging LLM Authorship Fingerprints with Targeted Rewriting
Model-attribution classifiers can often identify which language model produced a text, making model-specific writing patterns a signal of provenance.Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-Head
Scaling attention parameters can improve language model quality, but retaining full token histories makes additional heads costly at long contexts.OpenJev-RLCD: A Working RLCD Implementation
Decision models such as Jev answer questions with probabilities, which are only useful if they are calibrated.Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whether a failure reflects an intrinsic deficit in the targeted capability or a cascading error from…TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA
Finding a relevant paper is not the same as producing a verifiable answer from it.Audio Token Attention Is Predictable Before the Language Model Runs
A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one.VOSSA: Voiceprint Optimization for Streaming Speech Architectures
Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models.K2P: Label-Free Knowledge to Prompt Distillation
Knowledge distillation can transfer reasoning from stronger teachers to frozen students through reusable prompts, but avoiding weight updates does not eliminate supervision.