Papers by Khanh-Tung Tran
LaCoMSA: Language-Consistency Multilingual Self-Alignment with Latent Representation Rewarding (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing multilingual alignment methods mitigate these issues but rely on external supervision, such as translation systems or English-biased signal. |
| Approach: | They propose a preference optimization framework that leverages an LLM’s own latent representations as intrinsic supervision signals and rewards lower-resource language outputs based on their alignment with high-resourced (English) counterparts in the "semantic hub". |
| Outcome: | The proposed framework improves a Llama 3 8B model multilingual win rates by up to 6.8% absolute (55.0% relative) on X-AlpacaEval and achieves consistent gains across benchmarks and models. |
Disentangling Language Understanding and Reasoning Structures in Cross-lingual Chain-of-Thought Prompting (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has shown that cross-lingual chain-of-thought prompting improves learning in low-resource languages. |
| Approach: | They examine whether benefits of cross-lingual prompting arise from language-specific reasoning structures . authors employ neuron intervention and perturbation techniques to analyze and deactivate language-related reasoning neurons . |
| Outcome: | The proposed study shows that language-specific reasoning structures are essential for reasoning in each language, but have minimal effect on reasoning in other languages. |
Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Continued Pre-Training (CPT) enables Large Language Models (LLMs) to acquire second-language capabilities, yet the mechanisms underlying CPT remain poorly understood. |
| Approach: | They investigate how CPT adapts model representations across diverse language families and scripts, model sizes, and architectures. |
| Outcome: | The proposed model can be surgically transferred between base and CPT models with minimal loss. |