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 72
Poisoning-Based Backdoors Are Not Cryptographic
Defending against a backdoor requires recovering the verifier that decides whether an input is a trigger, since blocking individual triggers fails against an attacker who can generate new ones.On-Policy Transition Distillation
On-policy distillation (OPD) consolidates expert capabilities into a single student by matching teacher and student final-layer distributions on student-generated rollouts.Same Judgment, Different Yes: Measuring Multilingual Judgment Profiles in Language Models
Multilingual evaluations often score a model's opening yes or no, a token that also carries model and language answering conventions.Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts
LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public to confidential while disclosing only what the user is authorised to receive.BAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in News
Persuasive writing exploits cognitive biases, recruiting a reader's mental shortcuts to shape belief, often without the reader noticing.Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under Ambiguity
Large Language Models (LLMs) are increasingly used for interpersonal advice, potentially shaping how users interpret ambiguous social encounters.Occupational Uniqueness and Wage Growth
Changes in occupational task content may have different economic implications depending on whether the tasks gained or lost are occupation-specific or already widespread across the economy.Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models
Large Language Models (LLMs) depend fundamentally on the diversity, depth, and factual rigor of their pre-training corpora.Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs
Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of real-world knowledge.Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons
While the language model backbone is pretrained on text alone, large audio-language models (LALMs) can, to a great extent, recognize acoustic attributes, such as emotion, speaker gender, and spoken…Can Language Models Get "Aphasia" From Neuronal Ablation?
Progressive neuronal loss is the hallmark of neurodegenerative disease, yet how loss of neurons shapes the pattern of cognitive decline remains poorly understood.How Language Models Learn Taste: Brand Preference in LLMs
Asked to name a running shoe brand, language models say Nike.Forty Questions: Identifying a Language Model from One-Word Answers
A model behind an API can be identified from its one-word answers to everyday questions such as "Name a sound" or "Name a poet".Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling
Test-time scaling allocates additional inference compute to refining existing solutions or generating new ones.Reward Misspecification Degrades Chain-of-Thought Monitorability
Monitoring the chain-of-thought (CoT) of language models (LMs) is a key strategy for detecting and preventing misbehaviors for AI safety.From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution
Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires models to both identify the…Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed.Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter
Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score.DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge
Reliable retrieval-augmented generation (RAG) requires recognizing when neither retrieved documents nor parametric knowledge supports an answer.Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model.