14 hasil untuk "Han, Yo-Sub"
Menampilkan 1–14 · 0,10 detik · RSS
-
Buku Teks lengkap
Descriptional Complexity of Formal Systems: 23rd IFIPWG 1.02 International Conference, DCFS 2021, Virtual Event, September 5, 2021, Proceedings
Book Front Matter of LNCS 13037
-
Artikel Jurnal Teks lengkap
Ruleset Optimization on Isomorphic Oritatami Systems()
We study an optimization problem of a computational folding model, proving its hardness and proposing heuristic algorithms. RNA cotranscriptional folding refers to the phenomenon in which an RNA transcript folds upon itself while being synthesized out of a gene. An oritatami model (OM) is a…
-
Artikel Jurnal Teks lengkap
Computing the Shortest String and the Edit-Distance for Parsing Expression Languages
A distance between two languages is a useful tool to measure the language similarity, and is closely related to the intersection problem as well as the shortest string problem. A parsing expression grammar (PEG) is an unambiguous grammar such that the choice operator selects the first matching in…
-
Preprint Teks lengkap
From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text
Distinguishing human-written Korean text from fluent LLM outputs remains difficult even for trained readers, who can over-trust surface well-formedness. We present LREAD, a Korean-specific instantiation of a rubric-based expert-calibration framework for human attribution of LLM-generated text. In a…
-
Preprint Teks lengkap
Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
Identifying LLM-generated code through watermarking poses a challenge in preserving functional correctness. Previous methods rely on the assumption that watermarking high-entropy tokens effectively maintains output quality. Our analysis reveals a fundamental limitation of this assumption…
-
Preprint Teks lengkap
RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection
Hate speech remains prevalent in human society and continues to evolve in its forms and expressions. Modern advancements in internet and online anonymity accelerate its rapid spread and complicate its detection. However, hate speech datasets exhibit diverse characteristics primarily because they…
-
Preprint Teks lengkap
Steering Language Models Before They Speak: Logit-Level Interventions
Steering LLMs is essential for specialized applications such as style-sensitive text rewriting, user-adaptive communication, and toxicity mitigation. Current steering methods, such as prompting-based and activation-based approaches, are widely used to guide model behavior. However, activation-based…
-
Preprint Teks lengkap
A Linguistics-Aware LLM Watermarking via Syntactic Predictability
As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fostering a trustworthy AI ecosystem. A central challenge persists: balancing text quality against detection robustness. Recent…
-
Preprint Teks lengkap
How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs
Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms remain ineffective as they overlook the unique reasoning…
-
Preprint Teks lengkap
Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features
Recent progress in large language models (LLMs) for code generation has raised serious concerns about intellectual property protection. Malicious users can exploit LLMs to produce paraphrased versions of proprietary code that closely resemble the original. While the potential for LLM-assisted code…
-
Preprint Teks lengkap
CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
As safety concerns around large language models (LLMs) grow, understanding the internal mechanisms underlying refusal behavior has become increasingly important. Recent work has studied this behavior by identifying internal features associated with refusal and manipulating them to induce compliance…
-
Preprint Teks lengkap
ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
Current code generation evaluation measures functional correctness on well-formed inputs that satisfy all input preconditions. This paradigm has a critical limitation: task descriptions often leave these preconditions implicit, while evaluation filters out inputs that violate them. As a result…
-
Preprint Teks lengkap
ReSyn: A Generalized Recursive Regular Expression Synthesis Framework
…framework that decomposes complex synthesis problems into manageable sub-problems. We also introduce Set2Regex, a parameter-efficient synthesizer capturing the permutation invariance of examples. Experimental results demonstrate that ReSyn significantly boosts accuracy across various synthesizers…
-
Preprint Teks lengkap
KOTOX: A Korean Toxic Dataset for Deobfuscation and Detoxification
Online communication increasingly amplifies toxic language, and recent research actively explores methods for detecting and rewriting such content. Existing studies primarily focus on non-obfuscated text, which limits robustness in the situation where users intentionally disguise toxic expressions…