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 26
DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving
LLM-based theorem proving in Lean 4 has advanced rapidly, but provers are difficult to leverage newly contributed lemmas, because retrieval skews toward popular foundational lemmas, leaving the…Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models
This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers.CEFR Level Assessment across Languages and Text Granularities
Automatic assessment of textual CEFR levels is an important task in educational natural language processing.Digital sovereignty in professional translation workflows: a case study of migrating from Windows to Linux
This study examines digital sovereignty in professional translation through a screening of computer-assisted translation tools and translation management systems, and a case study of migrating a…SCRBench: Beyond Equivalence Checking for Semantic Change Reasoning in Code
Understanding how code changes affect program semantics is a core aspect of code reasoning in language models.BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion
Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or…Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away
We release Saidzoda-Tajik-LFM-2.6B, a Tajik adaptation of the 2.6B-parameter hybrid model LFM2.5-2.6B-Base, built for tool calling in Tajik on modest hardware.GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning
Reinforcement learning with verifiable rewards (RLVR) has recently been extended to vision-language models (VLMs), yet its effectiveness remains limited for text-rich reasoning tasks.When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs
Activation steering is an inference-time technique used to control or modify the behavior, tone, or safety properties of a large language model (LLM) without retraining the model's weights or…Does Reasoning Make Language Models Agree?
Language models face two opposing concerns: monoculture, in which models err in correlated ways, and multiplicity, in which equally accurate models make conflicting decisions.TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents
Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined.Precision--Recall Trade-off on the Inference Level for LLMs in Grammatical Error Correction
Large language models (LLMs) have recently been adopted for Grammatical Error Correction (GEC), achieving strong performance via both full fine-tuning and prompt-based approaches.GraphNIAH: A Benchmark for Long-Context Reasoning over Real-World Graphs
The needle-in-a-haystack (NIAH) benchmark was introduced as a test for measuring a model's ability to find small relevant facts within a very large body of input text.UpLoop: Training Looped Transformers via Upcycling at No Extra Pretraining Compute
Looped language models can strengthen reasoning through repeated computation with shared weights, increasing execution depth without adding independent parameters.From Training Exposure to Membership Evidence: A Controlled Study of OLMo 2
Yet most membership-inference (MI) evaluations on language models collect members and non-members after the fact, so success may reflect distribution shift and failure is inconclusive.Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction
Bangla symptom-based disease prediction is commonly evaluated on a small, imbalanced structured benchmark containing many profiles that differ by only one or two symptoms.Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components
Task Vectors (TVs) provide a compact way to steer large language models, but they are typically treated as atomized directions merely extracted from hidden states, leaving their internal functional…Stepwise-Querying: Distilling Reasoning without Access to Teacher Chain-of-Thought
Reasoning distillation is widely used to transfer the reasoning capabilities of large language models to smaller students through teacher-generated supervision.Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings
Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based…Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity
While sentence embeddings are primarily designed for semantic generalization, their latent geometry implicitly encodes surface-level lexical properties, a relationship that remains poorly understood.