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 134
Unreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical News
Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted.Time Delay System for Sequence Modeling
Existing sequence models share a critical limitation: they lack an explicit, interpretable mechanism for content-aware temporal recall.Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory
Long-term memory has been widely adopted in LLM-based agents to support persistent interaction and personalized assistance.Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation
In continuous diffusion language models (DLMs), latents generated by the diffusion prior are mapped almost deterministically to tokens, either by a decoder or through a token embedding matrix.SEEDS: Preview-Guided Evidence Admission for Search Agents
Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidence with consuming it.Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Decoder hidden states from different layers of large language models (LLMs) often encode complementary information.MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph
We introduce MVGraph, a benchmark for evaluating large vision-language models (LVLMs) on multi-graph reasoning where the evidence required by a query is distributed across multiple interrelated…SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents
We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents against psychologically grounded, resistant buyer…Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction
If a second text corpus were collected from the same population, how much would a predictor's outputs change?Language Models Have Interpretable Narrative Mechanisms
We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narrative properties.What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategies and behavioral…Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification
Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult.Evaluating LLM Creativity through Long-Tail Performance
Creativity benchmarks for large language models (LLMs) vary widely in task and metric design.EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
Continual learning requires models to accumulate past experience and transfer it to new tasks.Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution
Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements.GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs
Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly.RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models
Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the additional recurrent computation also increases…CoBe: A Benchmark For Conversational Counterfactual Text Editing
Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by that change.Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents
Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dead-end trajectories.CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation
Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding.