新闻
Is vibe coding ruining a generation of engineers?
AI tools are revolutionizing software development by automating repetitive tasks, refactoring bloated code, and identifying...
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
arXiv:2502.13962v2 Announce Type: replace Abstract: Scaling the test-time compute of large language models has demonstrated...
Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
arXiv:2510.01367v3 Announce Type: replace-cross Abstract: Reward hacking, where a reasoning model exploits loopholes in a...
Is In-Context Learning Learning?
arXiv:2509.10414v2 Announce Type: replace Abstract: In-context learning (ICL) allows some autoregressive models to solve tasks...
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
arXiv:2411.15993v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong capabilities in text...
Introspective Growth: Automatically Advancing LLM Expertise in Technology Judgment
arXiv:2505.12452v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly demonstrate signs of conceptual understanding...
Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction
arXiv:2509.14504v1 Announce Type: new Abstract: In this paper, we introduce OmniGEC, a collection of multilingual...
Interpreting the Latent Structure of Operator Precedence in Language Models
arXiv:2510.13908v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities but...
Interpretable Question Answering with Knowledge Graphs
arXiv:2510.19181v1 Announce Type: new Abstract: This paper presents a question answering system that operates exclusively...
Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
arXiv:2507.05137v2 Announce Type: replace Abstract: Learning Japanese vocabulary is a challenge for learners from Roman...
InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
arXiv:2510.21538v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet...
Internal World Models as Imagination Networks in Cognitive Agents
arXiv:2510.04391v1 Announce Type: cross Abstract: What is the computational objective of imagination? While classical interpretations...
