19 papers
Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
Quoc Phong Dao, Binh Anh Nguyen, Linh Ngo Van +3
While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-time int…
Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
Tien-Phat Nguyen, Truong Nguyen, Thanh-Thien Le +4
Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generate (Rouge…
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
Hoang Phan, Minh Pham, Chau Pham +3
On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward…
Orthogonal Witness Control for Muon Optimization via Sigmoid Spectral Reshaping
Dat Phi Van, Ngo Vu Minh, Tuc Nguyen +3
Matrix-valued optimizers such as Muon exploit the spectral structure of neural network updates through Newton--Schulz orthogonalization, but their near-flattening of the singular s…
HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answering
An Nguyen Phu, Dung Nguyen Quang, Luu Hieu An +3
Multi-hop question answering often fails when retrieval treats evidence as isolated matches to the original question, since the facts needed to answer a complex question are usuall…
TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation
Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi +4
Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to stric…
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van +3
Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even thou…
LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models
Minh Chu Xuan, Tien-Phat Nguyen, Linh Ngo Van +3
Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or we…
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan +4
Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenanc…
MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation
Pham Khanh Chi, Quoc Phong Dao, Thuat Nguyen +3
Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, igno…
SRA: Span Representation Alignment for Large Language Model Distillation
Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi +4
Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While exi…
MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining
Phung Gia Huy, Hai An Vu, Minh-Phuc Truong +4
Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) of…
Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
Tien-Phat Nguyen, Truong Nguyen, Minh-Phuc Truong +3
Muon orthogonalizes the momentum buffer before each update, replacing its singular values with ones via Newton-Schulz iterations. This simple change lets Muon tolerate far larger l…
Selective Off-Policy Reference Tuning with Plan Guidance
Duc Anh Le, Anh Duc, Tien-Phat Nguyen +3
Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update for those fa…
BSO: Safety Alignment Is Density Ratio Matching
Tien-Phat Nguyen, Truong Nguyen, Thin Nguyen +3
Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual update…
CTPD: Cross Tokenizer Preference Distillation
Truong Nguyen, Phi Van Dat, Ngan Nguyen +3
While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplore…
Sharpness-Guided Group Relative Policy Optimization via Probability Shaping
Tue Le, Linh Ngo Van, Trung Le
Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a wid…
XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
Tien Phat Nguyen, Vu Minh Ngo, Tung Nguyen +4
Cross-lingual topic modeling aims to uncover shared semantic themes across languages. Several methods have been proposed to address this problem, leveraging both traditional and ne…
CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers
Anh Duc Le, Tu Vu, Nam Le Hai +4
Large Language Models (LLMs) achieve state-of-the-art performance across various NLP tasks but face deployment challenges due to high computational costs and memory constraints. Kn…