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 133
What Drives AI Citations? Content, Retrieval and Model Knowledge in Generative Engine Optimization (GEO)
Generative search engines such as ChatGPT, Gemini and Perplexity now decide which Web pages users see as sources, and a growing industry of generative engine optimization advises publishers on how…PAT: A Personality-Driven Augmentation and Transfer Learning Framework for Depression Detection on Social Media
Depression is a prevalent mental disorder that affects millions worldwide, with early detection crucial for effective intervention.Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses
Large language models can post-edit ASR by using linguistic context to compare N-best hypotheses and rewrite the transcript when needed, often improving WER without retraining the recognizer.Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions
Argument structures represent how individual arguments interact within a discourse.RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs
Extracting structured information from regulatory documents is a critical but challenging task.Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models
When a large language model refuses an unethical request, what does refusal mean?Compute-Optimal Scaling Laws for Spiking Language Models
Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale.Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations
Large language model (LLM) assistants are increasingly used in multi-turn conversations, where the user's intent is often unclear at first and revealed only gradually over time.Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI
We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis.Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry
A language model's ability to solve a task individually does not ensure that a team can solve it under unequal access to information and communication.Active Learning for Finding a Needle in a Haystack
Training a classifier to find a rare class of documents, such as hate speech directed at a particular religious group, requires labelled examples that are expensive to obtain when the class makes up…UDHRBench: Benchmarking Human Rights in Large Language Models
Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human rights standards remains…Word-Aligned Prosody Reflects Speaker Differences More Than Depression or PTSD Severity
Word-aligned prosody is increasingly used to detect depression and posttraumatic stress disorder (PTSD), yet the stability and clinical relevance of these measurements remain unclear.SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG
Retrieval-augmented generation (RAG) reuses the same documents across many requests, making non-prefix KV-cache reuse attractive.Do LLMs differentiate linguistic traits internally?: A layer-wise analysis
Large language models often produce judgments that resemble human responses, but it remains unclear whether they internally capture linguistic nuances such as conventional versus idiomatic meaning.Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety alignment and induce harmful responses.PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next.When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks
Web agents increasingly browse, interpret, and act on web content on behalf of users.COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments.Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets
Emotion classifiers are routinely applied beyond their training data, on the assumption that same-named labels such as fear or surprise mean the same thing across resources.