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 18 September 2026 to 6 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 225
Trust and Task Completion in the World of Consumer AI Agents
Action agents do things for people.PACT: Pairwise-Anchored Calibrated Tuning for Single-Token Typed Decisions
Single-token typed-decision models answer a schema question by reading the logits of a few one-letter answer codes at a single position: they are fast and return a probability for every allowed…The Price of Token Boundaries: Compression Certificates and Prediction
Pre-tokenisation restricts which text fragments can become prediction units, but its compression cost is obscured when tokenisers are compared only under the same boundaries.CruxBench: A Benchmark of Information Discovery
Benchmarks for large language models (LLMs) typically evaluate the accuracy of answers against fixed reference labels.Recursive Self-Improvement via On-Policy Distillation for Reasoning
On-policy distillation (OPD) trains a student model by having it generate trajectories, then matching its next-token predictions with an external teacher's next-token predictions.Prompt Injection Detection for Email Agents Through Attack Chain Modeling
Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into the model context and influence subsequent tool…TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history…LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information
"System One" decision models such as TypeSafe's Jev and its open counterpart Laya answer typed questions about a text in a single forward pass with calibrated probabilities, but they cannot ask for…Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4
When a language model receives two conflicting documents as input, how does it decide which one to prioritize?Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache Eviction
KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window.SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages
Multilingual text-vision embedding models are essential for cross-lingual image-text retrieval, but Southeast Asian languages remain poorly supported due to the region's linguistic diversity and…Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance
Tandem speech-to-speech architectures couple a responsive speech frontend with an asynchronous text backend.Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models
This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights.Understanding the Role of Prompt Template in Knowledge Distillation for Safety Alignment
Prior research has demonstrated that the choice of prompt template during Supervised Fine-Tuning (SFT) significantly impacts the robustness of safety alignment afterwards.Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness
Looped transformers reuse weights across recurrence steps, making low-bit quantization especially attractive.I-Parakeet: Integer-Only Conformer ASR on Mobile NPU
In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without any floating-point operator or CPU fallback.Enhancing Assessment of Self-Consistency in LLM Explanations using Perturbation Strength
Prior work has examined the self-consistency of LLM-generated explanations using surface-level perturbation methods.Persistent Negatives for Adversarial Black-Box On-Policy Distillation
Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token probabilities.Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptions remains challenging.Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos
Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are provided in full or compressed through…