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 11
Residual Attribute Leakage Is an Interface: Auditing Privacy Evaluation After Text De-identification
A privacy evaluation of de-identified text asks a language model (the adversary) to guess a person's protected attribute.HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias
Historical archives are invaluable for multidisciplinary research but remain inaccessible globally due to severe language barriers.Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation?
Knowledge distillation improves a student model's reasoning ability through supervision from a teacher.Who is the Pronoun Pro? Comparing LLMs and Humans at Number-Disambiguation of 'they'
This study evaluates whether large language models (LLMs) can reliably replace or complement human research assistants in linguistically complex annotation.Whose Effect Is It? How Objectives Inflate Learned Subspace Interventions
Interpretability often locates concepts by copying part of a language model's state from one input into another (activation patching).ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows.The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory
Speech large language models retain audio history to support multi-turn conversations.GM League Arena: An Interactive Long-Horizon Task Benchmark Based on Professional Sports League Management
Long-horizon decision-making under sustained competition requires large language models (LLMs) to balance immediate investment with future resource needs.When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering
Financial question answering can fail even when a model extracts a plausible number from the supplied evidence: the answer may attach it to the wrong entity, period, unit, or accounting concept.What Does the Model See? Representation Validity in Multimodal LLM-Based Video Analysis
Multimodal large language models (MLLMs) allow social scientists to analyze video at scale, but researchers must decide which parts of a video to provide as input.ARLoop: Fully-Open Pre-trained Looped Transformers with Attention Residuals
Looped transformers increase effective depth by repeatedly applying a shared set of transformer layers, offering a parameter-efficient way to scale computation.Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve
Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations.Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
Fine-tuning a large language model (LLM) on harmful data in a narrow domain, such as bad medical advice, can make it broadly misaligned.Personas Are Not People: Identity as State, Not Attribute
Synthetic populations, large sets of simulated people, are increasingly used in place of real people to pretest surveys, simulate users and communities, and evaluate AI systems.LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers
Looped transformers are a parameter-efficient alternative to standard transformers for language modeling.MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
Skill memories encode past experiences as textual prompts to improve reinforcement learning (RL) for self-evolving agents.MedPhysBench: A Benchmark for Evaluating Language Models on Medical Physics Calculations and Error Detection
Medical physicists turn a prescription into a delivered dose and check one another's calculations, because one error in a beam calibration or a monitor-unit (MU) calculation can affect every patient…A Circuit for In-Context Learning
In-context learning (ICL) lets a pretrained language model perform a task specified by demonstrations in its prompt, with no parameter updates.Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits
When a language model answers, we can usually only estimate why.Suppressing Misaligned Behaviors in Language Models, Durably
Undesired model behaviors can emerge or re-emerge at any stage of training.