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 48
Beyond Belief: Evaluating and Mitigating LLM Susceptibility to Misinformation
Tool-using large language models (LLMs) must decide whether external information warrants action."High-Quality" Data for Early-Stage Instruction Tuning: An Empirical Study of Data Quality Metrics
"Data quality" is widely invoked in instruction tuning, but the term is often underspecified.Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine
Professionals send working documents to external large language models.The Patient Is Always Right? Evaluating Sycophancy in Medical Diagnosis with Graded Patient Beliefs
More people are seeking out general-purpose AI models for medical advice, including diagnosis.When Does GEPA Merge Help? A Mechanism-Level Diagnostic
GEPA is among the strongest reflective prompt optimizers for language-model programs, but its system-aware merge operator is unstable across models: merge improves gpt-4.1-mini on average while…Memory Tax: Dissecting the Net Value of Agent Memory
Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear.Identically Trained Language Models Break on Different Jailbreaks
Jailbreak benchmarks test one checkpoint and treat which jailbreaks break it as a property of its pretraining data and safety training.The LALA Benchmark: Evaluating Literary and Linguistic Analysis in LLMs
We introduce the Literature and Linguistics Analysis Benchmark (LALA), comprising 236 open-ended questions written by experts in linguistics and literary studies, together with expert-provided ideal…T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding
Speculative decoding significantly accelerates autoregressive text generation in Large Language Models (LLMs), but its efficacy depends largely on two key factors: the distributional alignment…Can LLMs Trust Appropriately? Evaluating Calibrated Reliance on Imperfect Partners
Large language models increasingly collaborate with humans and peer AI agents whose contributions may be incomplete, inconsistent, or incorrect.Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
Reinforcement learning with verifiable rewards (RLVR) enables large language models (LLMs) to continuously self-improve their reasoning capabilities.Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction
Long-context language models can increasingly process entire documents, making full-context prompting a practical alternative to passage retrieval.Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?
While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily evaluated through static, passive observation.Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents
Tool-using language model agents are usually evaluated by whether they finish the user's task.Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning
Latent reasoning performs intermediate computation in continuous space rather than through explicit tokens, which is particularly appealing in chemistry, where errors in explicit reasoning can…Write What Matters: Disentangling Token Selection from Slot Allocation in Recurrent Memory
Long-sequence models must retain earlier information.Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback
Supervised Fine-Tuning (SFT) of LLMs suffers from catastrophic forgetting, and prevailing mitigation strategies struggle to reconcile the plasticity-stability dilemma.MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding
Modern surgical AI increasingly requires multimodal understanding rather than isolated perception, yet existing datasets remain largely limited to single-task supervision such as recognition or…Higher Reasoning Effort Improves Reference Verifiability and Changes Reasoning Summaries in GPT-5.5
Large language models are increasingly being used in different stages of scientific knowledge production, including the suggestion of references.Synthetic linguistic data
Synthetic linguistic data have become increasingly prominent in linguistic research, from the analysis of large collections of AI-generated texts to controlled experiments investigating grammatical…