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 131
Evaluating Semantic Relation Knowledge through Bidirectional Relation Prediction from Gloss Pairs
Semantic relations organise word senses and are fundamental to lexical semantics.Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk
Executable tests grade large language model (LLM) coding-agent patches for leaderboards, rewards and self-improvement.Evaluating Bias in Chinese Large Language Models across Tasks and Registers: Task Operationalization Effects and Irony Classification Risks
In Chinese content governance, large language models are increasingly used to identify toxic and discriminatory expressions, yet both task operationalization and ironic expression can alter bias…EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model
Deploying language models (LMs) on the edge presents unique memory, latency, and power challenges absent in high-performance computing.Scale, Drivers, and Limits of Representational Alignment Across Large Language Models
Comparing large language models can reveal shared representational structure and systematic differences between them.AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation
While language therapy is the primary treatment for post-stroke aphasia, limited clinical resources often restrict patient access to proper care.Query-Adaptive Neuron Steering for LLMs
Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge.LongHisDoc: A Comprehensive Benchmark for Chinese Long Historical Document Understanding
Chinese historical documents are invaluable cultural treasures, but their complexity poses significant comprehension challenges for non-specialists.Reward-Aligned Distillation
Reinforcement learning with verifiable rewards improves the reasoning capabilities of large language models, but remains computationally expensive and sample inefficient.Uniform Information Density-Based Preference Optimization
To enable large language models to generate outputs that align with human preferences, optimization algorithms based on the comparison between chosen and rejected output pairs have been developed…Fine-Tuning Strategy, Not Just Data: A Statistically Rigorous Audit of Gender and Stereotypical Bias in Embedding Models for HR Recommendation Systems
Embedding models underpin modern job-candidate matching: resumes, job descriptions, and queries are encoded as dense vectors, and recommendations come from nearest-neighbor retrieval over that space.Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning
Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information.The Company a Question Keeps: Auditing Open Jev-Style Models for Retrieval
Jev's documented interface evaluates typed questions independently against shared evidence.PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models
Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks.VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS
Instruction-following text-to-speech (TTS) typically leaves voice design implicit, as conventional speaker embeddings encode reference audio rather than text-driven targets.Towards Merging-conditional Backdoor Unalignment against Large Language Models
Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training.Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging because prescription decisions require integrating…How to Build a Benchmark That Actually Measures Taste
Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test.Vela: User Behavior as Supervision Sparks LLM Intelligence
Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems.Amharic-English Cross-Language Question Answering Using Statistical Machine Translation, Named Entity Recognition, and Semantic Indexing
The predominance of English-language Web content creates an information-access barrier for speakers of low-resource languages such as Amharic.