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 116
Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions…Swiss4Arg: A Parallel Dataset for Multilingual Argument Mining across Swiss National Languages
We present Swiss4Arg, a multilingual dataset for argument mining based on official Swiss voting brochures, covering all four national languages: German, French, Italian, and Romansh (a Romance…Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features
Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational.Text-Only vs. Image-Aware VLM Judges for Manga Translation Evaluation
In manga translation, visual context outside speech-bubble text, including speaker identities, referents, and scene tone, is depicted in page images, making it natural to refer to images during…Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models
As generative language models become more capable and widely used, inference demand grows, making efficient serving increasingly important.HaloBlock: Faster and Better Decoding for Diffusion Large Language Models
Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding.Agent-Reflex: Teaching Language Agents to Act Reflectively
Large language models have evolved from single-turn chatbots into interactive agents capable of long-horizon reasoning.Virtual Head Attention
The design of attention mechanisms in long-context large language models faces an ``impossible triangle'' among KV cache size, training and prefill FLOPs, and model quality.Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models
A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view.Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models
Diffusion language models (DLMs) enable flexible parallel generation by resolving tokens according to the model's evolving predictability rather than a fixed left-to-right order.Fish Audio Drama 3 Technical Report
We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters…LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems
Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks.Machine--human agreement in marking undergraduate assignments is specific to model, prompt and institution
Large language models (LLMs) promise to automate one of higher education's most resource-intensive activities: assessing student writing.inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
This work investigates the application of the Membership Inference Test (MINT) to large language models (LLMs) fine-tuned with LoRA, aiming to determine whether specific samples were used during…A Benchmark for Bangla Task-Oriented Dialogue Understanding
Task-oriented dialogue understanding remains underexplored for Bangla, particularly in multilingual settings involving English and romanized Bangla (Banglish).From Agents to Edges: Paired Optimization for Multi-Agent Collaboration
Strong individual agents do not guarantee effective collaboration.Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems.Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering
Do language models carry information about narrative events before writing them, and how far ahead?Cheap, Consistent, Calibrated, but Biased? Typed Decision Models as Judges
Typed decision models (TDMs) return a probability for each allowed answer instead of generating text, which makes them candidates for cheaply replacing LLM judges that compare two answers.Monitoring latent reasoning in looped language models
Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost.