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 124
REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces
Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents.ATTCK-R: Knowledge-Aware Long-Horizon Jailbreaking for Protected LLMs
As large language models are deployed behind increasingly sophisticated safety mechanisms, evaluating their robustness under realistic adversarial conditions becomes increasingly difficult and…Strong yet Controllable LLM Abstention without Learning to Abstain
Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong.RIFT: Token Influence Follows the Path of Least Resistance
Which context tokens drive a language model's answer?A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes
Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs).Self-Distillation with Verbal Regularization
On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student.HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision
Multilingual translation requires a model to preserve meaning while producing text in a requested language.Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs
Large language models are increasingly deployed in morally and legally sensitive contexts, yet little is known about how they internally represent distinctions between moral reasoning styles.PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization
Although users may express different personalization needs across tasks, these task-specific behaviors can reflect shared underlying preference mechanisms.RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning
Multi-step retrosynthesis planning is often considered solved once a route to purchasable starting materials is found, but such a route should also be practical in real-world chemistry.CultureBot: A Framework for Retrieval-Augmented Exploration of Cultural Heritage Data
Digital cultural heritage collections encode rich relations among objects, places, periods, providers, images, and source institutions, yet users typically access them through keyword search and…ARMED: Adaptive Retrieval-Augmented Medication Recommendation
Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions.VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric
Current image-text evaluation often relies on a global score, which gives limited insight into which semantic details are supported by the image.CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds
The growing use of language models for forecasting motivates a broader evaluation of their world-model capabilities.Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about political beliefs…The interpreter as developer: An autoethnographic design study of building a computer-assisted interpreting tool through human-LLM co-creation
Real-time AI captioning now serves audiences at multilingual events, yet computer-assisted interpreting (CAI) tools are still built for interpreters, rarely by them.PATMT2: Two-stage domain adaptation for multilingual patent translation
We present PatMT2 (Patent Machine Translation, v2), a two-stage LoRA pipeline that adapts the Hy-MT2-7B dedicated translation model to four-language (Chinese/English/Japanese/Korean) patent…Ontology-Based Post-Coordinated Expression Assembly: from Clinical Narrative to Queryable Knowledge Graphs
Clinical oncology documentation records decisive information in free text, where it remains readable but not retrievable at scale, leaving cohort identification dependent on incomplete diagnostic…Communication, Vocalisation, and Language
The contention is that the current batch of Large Language Models don't *understand* language, but they *do* it.Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models
In parallel decoding, diffusion language models commit several tokens per forward pass, so co-committed tokens cannot see each other, breaking multi-token format units that parsers need.