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 191
Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations
Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest.Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior
Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT).Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Chain-of-thought monitoring as an approach for AI oversight and control is threatened by the possibility of steganographic reasoning, where LLMs conceal their reasoning inside innocuous-looking text.When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models
We investigate the problem of role-capability leakage (RCL), in which a role-prompted reasoning model generates convincing in-role text while continuing to exhibit capabilities on benchmarks that…Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models
Role-playing prompting has become a popular yet simple technique for improving LLM reasoning and output quality.FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
Large language models frequently fail to balance staying truthful with being supportive.GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning
Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic quality when the model's preferred outputs are poorly aligned with the imposed grammar.LLM Persona Unlearning
Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals.OPSRD: On-Policy Self-Role Distillation
Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on demanding tasks.The Concrete-Arbitrary Gap: Kinship Reasoning in LLMs Is Not Indifferent to Presentation
We test whether large language models solve formally matched kinship problems equally well when relations are expressed in familiar vocabulary or by explicitly defined nonce predicates.MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models
Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as model size decreases.AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization
Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts.RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures
Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distinguishing nearby positions.LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes…UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding
Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass.Overview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
This paper presents an overview of the fourteenth edition of the BioASQ challenge, organized in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2026.Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution.OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories.MGhana-ST: A Low-Resource Speech Translation Dataset for Ghanaian Languages and an Analysis of Multilingual Training Trade-offs
We present MGhana-ST, a speech translation dataset for four low-resource Ghanaian language varieties: Ga, Twi (Akuapem and Asante), Ewe, and Fante.LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models
Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback.