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 229
Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bit
We ask how GGUF quantization affects agentic tool use in Polish and whether the effects generalize across models.EngramRAG: Dynamic Usage-Weighted Topology and Synaptic Consolidation for Multi-Hop Agentic Memory
As autonomous LLM agents are deployed across multi-session environments, conventional memory architectures suffer from Associative Blindness (inability to traverse multi-hop relational…mu-bench: A Multilingual Utterance Transcription Benchmark
Voice agents depend on accurate automatic speech recognition (ASR) to act on what callers say, yet ASR is evaluated on read, English-centric speech with word error rate (WER), which penalizes…On Evaluating and Improving Conversational Agents in Production
We present a framework for evaluating and improving a large-scale, multi-agent shopping assistant in production, and report lessons from its use.Hyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling
Macroeconomic productivity metrics, such as Total Factor Productivity, register technological breakthroughs with multi-year reporting lags due to administrative survey intervals and national…The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable.Resolving the Missing Financial Data Crisis: A Generative AI Pipeline for SEC 10-K Extraction
SEC 10-K filings contain substantial financial information that is not consistently captured in structured datasets, creating a missing-data problem affecting over 70% of firms and half of total…Regime Boundary Alignment for Evidence-Gated Question Answering
Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence is missing.Learning New Words from Unlabeled Test Data in Automatic Speech Recognition
New words are invented every day.Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS
We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's…Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms
Despite strong performance on standard benchmarks, it remains unclear whether large language models (LLMs) evaluate social pragmatics in ways that align with human judgments.MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks
Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality persistently degrades.Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots
General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands and generate multi-step action sequences in real…Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues
Emotion dynamics are critical for understanding crisis-support conversations, yet most computational work treats emotion as static utterance-level labels.CRISS: A Retrieval-Augmented AI Chatbot for Assisting Cancer Registrars
Cancer registrars, including Oncology Data Specialists (ODSs), must interpret complex and frequently updated coding and staging standards.Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study
We replicate the distributional-semantics extractive summarisation method of Mohd, Jan and Shah (2020) and adapt it to Hindi, substituting a Devanagari-appropriate component at every…ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks
Fully continuous diffusion language models (dLMs) denoise continuous representations without intermediate discretization, then decode all response tokens in parallel at the final step.Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech.Tag-Aware Structured Text Translation: Towards a Systematic Understanding
Internet texts are replete with format tags that carry structural, semantic, and functional meaning.BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech
Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech.