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 37
A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs
Do vision-language models (VLMs) share our ability to communicate visually?AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation
Cross-modal translation requires models to capture shared semantics across modalities while preserving the fine-grained structure required by the target modality.Do AI Scientists Know What's New?
A major challenge facing AI scientific discovery pipelines is how to determine when a generated idea is meaningfully novel.MedConstBench: Benchmarking How Constitutions Steer LLMs in Medical Ethics
As large language models advance rapidly, they are increasingly used to answer medical questions, and many such models are now deployed locally.Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels
Attention Matching (AM) compacts a KV cache by keeping some keys per head, refitting their values and adding a bias to each kept key's logit.Benchmarking Task Takeover Across Agent Handoffs
As agents collaborate on longer tasks, responsibility may pass between models before the work is complete.Causal Localization of Evidence Effects in Transformers
Can controlled symbolic inputs reveal attention heads that influence a language model's decisions from natural language evidence?ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization
Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal.RoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding
Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions.Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization
Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora.PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy
Final-answer accuracy reports whether a vision-language model was right, but not whether its answer was grounded in the image, whether its stated reasoning reflects that evidence, or what the answer…QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG
Chunking is a fundamental preprocessing step in retrieval-augmented generation (RAG), yet most existing chunkers rely primarily on heuristics.Decoupling Consistency and Conflict across MLLM Layers for Fake News Detection
The trustworthiness of Web content faces a growing threat from multimodal fake news.Structured Maps for Landmark-Based Route Instructions with LLMs
To generate landmark-based route instructions, models must understand both map geometry and human landmark preferences.Balanced State Subspaces for Mamba-2 State Compression
Mamba-2 compresses all context into a fixed-size recurrent state that dominates decoding memory and bandwidth.Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs
Discourse parsing based on Segmented Discourse Representation Theory (SDRT) is crucial for capturing the structural dynamics of dialogues.A Quantitative Approach to Asch Conformity in Frontier Large Language Models
The Asch conformity experiment has recently gained considerable attention as a way of measuring conformity in large language models (LLMs).Specialization, Diversity, and Scaling in Child-Scale Language Models
Modern language models are trained on far more language than children experience, but we know much less about learning from small, naturalistic datasets.Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces
Reasoning language models answer math problems by writing long chains of thought, and sampling many chains per problem and taking a majority vote raises accuracy at a large cost in generated text.A Harness Reducing over-Defensive Writing in Agents by Isolating Objections
When expanding a report, writing with agents may introduce a stronger claim than the article makes and then disclaim it.