From the 1 of 10 linked papers with an AI index.
10 papers
LAMAR: An Open Language-Aware Multilingual Alignment Reranker
Seongtae Hong, Youngjoon Jang, Jungseob Lee +2
In multilingual retrieval augmented generation pipelines, an embedding model can retrieve relevant documents written in multiple languages, which are subsequently reranked before a…
Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
Jungseob Lee, Seungyoon Lee, Suhyune Son +4
The paper shows that conditioning large language models on the correct answer when generating chains of thought harms the quality of distilled reasoning data, leading to large drop…
Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards
Jungseob Lee, Seungyoon Lee, Seongtae Hong +3
Training large language models to reason efficiently is a critical challenge. While integrating length-penalizing rewards into Group Relative Policy Optimization (GRPO) aims to red…
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5
Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk fo…
Parallel Test-Time Scaling with Multi-Sequence Verifiers
Yegon Kim, Seungyoo Lee, Chaeyun Jang +2
Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it i…
CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training
Seungyoon Lee, Minhyuk Kim, Seongtae Hong +3
Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignmen…