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 202
Effective Dense Retrieval using Only In-Context Examples
Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training.Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs
Speech-LLMs are expensive to run, making compression important for real-world deployment.Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces
Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning.How Local Mixing Encodes Relative Position in Global NoPE Attention
The attention operation is naively position invariant.From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
Vision-language models (VLMs) may accept false visual premises, answering questions about a target object's color, count, location, or state even when it is absent.LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning
Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute.AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
A small trainable advisor can steer a frozen language-model executor using natural-language advice.Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Agent performance depends on both reasoning ability and the environment in which it acts.Pretraining Latent Information Feedback Transformers with Teacher Supervision
Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for information to flow downward across generation steps…Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Answering questions about long videos often requires connecting events involving the same objects across hours or days.EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional training is costly in both computation and…STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving.Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs).Framing the Narrative: Ideological Mimicry in Large Language Models
Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's stance as a relatively stable property.ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
Values such as honesty, autonomy, and confidentiality are often regarded as general principles underpinning AI alignment.NinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space
In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different architecture families with a single trained…Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive differences.HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control
Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe action in…Multi-agent discussion gains less when dissent is withheld
Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable.Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
Test-time scaling improves model performance by allocating additional compute during inference.