arXiv subjects

Yifan Le

Publications and source records attributed to Yifan Le.

4 recordsLinked to original sources

arXiv2026

YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning

Preference optimization has become an important post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically rely on externally constructed preference data, using preferred and dispreferred responses as sample-level supervision. However, such external signals rarely make explicit use of capability-related information contained in the model's internal representations. For mathematical reasoning, certain neuron groups may exhibit activation patterns associated with mathematical knowledge, symbolic manipulation, or logical reasoning. Similar to reflexive behavioral signals, these internal activations may provide a coarse indication of whether the model is engaging math-related capabilities.We introduce YFPO, short for Yoked Feature Preference Optimization, a preliminary neuron-guided preference optimization framework for mathematical reasoning. YFPO first uses AttnLRP to identify math-related neurons, and then constructs an auxiliary reward from their activation margin between preferred and dispreferred responses. This design augments external preference learning with internal neuron-level signals. We conduct preliminary experiments on a small-scale language model using GSM8K as the main benchmark. Results suggest that neuron-level signals can interact with preference optimization and occasionally improve reasoning performance, offering a promising direction for more fine-grained and interpretable reasoning-oriented post-training.

cs.CL↗

arXiv2026

Schema Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding

Constrained decoding is widely used to make large language models produce structured outputs that satisfy schemas such as JSON. Existing work mainly treats schemas as structural constraints, overlooking that schema-key tokens also enter the autoregressive context and may guide generation. To the best of our knowledge, we present the first systematic study of schema keys as an implicit instruction channel under constrained decoding. We formulate structured generation as a multi-channel instruction problem, where task signals can be placed in prompts, schema keys, or both. We further provide a projection-aware analysis: a CoT-style key helps only when its semantic gain exceeds the distortion induced by grammar-constrained projection, offering a theoretical explanation for model-dependent key effects. Experiments on mathematical reasoning benchmarks show that changing only schema-key wording can substantially affect accuracy while keeping the prompt, model, output structure, and decoding setup fixed. Qwen models tend to benefit more from schema-level instructions, whereas LLaMA models rely more on prompt-level guidance, and the two channels interact non-additively. Our findings show that schema design is not merely output formatting, but part of instruction specification in structured generation.

cs.CL↗

arXiv2026

CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models

Multilingual large language models (LLMs) achieve strong performance across languages, yet how language capabilities are organized at the neuron level remains poorly understood. Prior work has identified language-related neurons mainly through activation-based heuristics, which conflate language preference with functional importance. We propose CRANE, a relevance-based analysis framework that redefines language specificity in terms of functional necessity, identifying language-specific neurons through targeted neuron-level interventions. CRANE characterizes neuron specialization by their contribution to language-conditioned predictions rather than activation magnitude. Our implementation will be made publicly available. Neuron-level interventions reveal a consistent asymmetric pattern: masking neurons relevant to a target language selectively degrades performance on that language while preserving performance on other languages to a substantial extent, indicating language-selective but non-exclusive neuron specializations. Experiments on English, Chinese, and Vietnamese across multiple benchmarks, together with a dedicated relevance-based metric and base-to-chat model transfer analysis, show that CRANE isolates language-specific components more precisely than activation-based methods.

cs.CL↗

arXiv2024

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among various jailbreak methods, there is no standard implementation framework available for the community, which limits comprehensive security evaluations. This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs. It builds jailbreak attacks using four components: Selector, Mutator, Constraint, and Evaluator. This modular framework enables researchers to easily construct attacks from combinations of novel and existing components. So far, EasyJailbreak supports 11 distinct jailbreak methods and facilitates the security validation of a broad spectrum of LLMs. Our validation across 10 distinct LLMs reveals a significant vulnerability, with an average breach probability of 60% under various jailbreaking attacks. Notably, even advanced models like GPT-3.5-Turbo and GPT-4 exhibit average Attack Success Rates (ASR) of 57% and 33%, respectively. We have released a wealth of resources for researchers, including a web platform, PyPI published package, screencast video, and experimental outputs.

cs.CL↗