Papers by Se-Young Yun
Large Language Models Are Reasoning Teachers (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks step-by-step. |
| Approach: | They propose a method that uses large model samples as reasoning teachers to fine-tune smaller models. |
| Outcome: | The proposed method outperforms prompt-based methods and the teacher model in many tasks and extends it by leveraging the teacher's ability to generate multiple rationales for each original sample. |
Self-Training Elicits Concise Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-thought reasoning has enabled large language models to use additional computation through intermediate tokens to solve complex tasks, but current models often generate more tokens than necessary to accomplish the task, incurring extraneous inference costs. |
| Approach: | They propose to fine-tune models with self-generated concise reasoning paths obtained by best-of-N sampling and few-shot conditioning in task-specific settings to elicit concise reasoning. |
| Outcome: | The proposed method reduces output tokens by 30% on GSM8K and MATH while maintaining average accuracy. |
MERIT Feedback Elicits Better Bargaining in LLM Negotiators (2026.acl-long)
Copied to clipboard
| Challenge: | Empirical results indicate that baseline LLM strategies diverge from human preferences, while our mechanism substantially improves negotiation performance. |
| Approach: | They propose a utility feedback centric framework that measures human-aligned, economically grounded metrics that implicitly measure how well the negotiation aligns with human preference. |
| Outcome: | The proposed framework significantly improves negotiation performance, yielding deeper strategic behavior and stronger opponent awareness. |
Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances have introduced GER frameworks that utilize LLMs to refine ASR outputs. |
| Approach: | They propose a framework that allows a large language model to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition models. |
| Outcome: | The proposed framework achieves 57.7% error rate gain over standard ASR baseline, compared to single-stream approaches that achieve only 10% gain. |
Multi-Drafter Speculative Decoding with Alignment Feedback (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to accelerate large language model (LLM) inference use a smaller model to draft future tokens, which are then verified by the target LLM. |
| Approach: | They propose a unified framework that integrates multiple drafters into the SD process. |
| Outcome: | Extensive experiments show that MetaSD outperforms single-drafter approaches. |
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent benchmarks have attempted to identify and explain hate speech but lack the reasoning to supervise detection models. |
| Approach: | They propose a framework that uses large language models to fill in the gaps in hate speech explanations by using existing annotations. |
| Outcome: | The proposed framework outperforms baselines on SBIC and Implicit Hate using model-generated data and improves generalization to unseen datasets. |
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized natural language processing and are limited by high inference time in multilingual settings. |
| Approach: | They propose a training recipe for an assistant model in speculative decoding, which are leveraged to draft and-then its future tokens are verified by the target LLM. |
| Outcome: | The proposed model significantly speeds up inference time and out-of-domain speedup across various languages. |
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Vision-language models (VLMs) have demonstrated remarkable applicability across downstream tasks, including zero-shot image classification. |
| Approach: | They propose an efficient transfer learning method that integrates visual prompts and text adapters with pre-trained VLMs to achieve optimal performance for any target domain. |
| Outcome: | The proposed method outperforms baselines on unseen tasks. |
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures. |
| Approach: | They propose a framework that narrows the encoder and shortens the decoder networks of encoder-decoder models. |
| Outcome: | The proposed framework reduces the number of decoder layers and improves generation quality. |
C2: Scalable Auto-Feedback for LLM-based Chart Generation (2025.naacl-long)
Copied to clipboard
Woosung Koh, Janghan Yoon, MinHyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Se-Young Yun, Youngjae Yu, Bongshin Lee
| Challenge: | generating high-quality charts with Large Language Models presents significant challenges due to limited data and the high cost of curation. |
| Approach: | They propose a referencefree automatic feedback generator to generate high-quality charts with Large Language Models. |
| Outcome: | The proposed framework outperforms baselines and shows that it significantly improves data diversity. |
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for knowledge distillation (KD) are prone to overfitting to training datasets . recent advances in NLP have shown that using PLMs such as BERT and RoBERTa on downstream tasks is effective. |
| Approach: | They propose a consistency-regularized knowledge distillation method which mitigates overfitting of existing methods. |
| Outcome: | The proposed method outperforms existing methods on the GLUE benchmark and synthetic datasets. |
Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Current language models are trained on static data, implying that the encoded knowledge could go wrong as time passes. |
| Approach: | They propose a temporally evolving question-answering benchmark for language models . they use Wikipedia databases to test language models for dynamic knowledge in ever-changing world . |
| Outcome: | The proposed task aims to model the evolution-adaptability of language models in the real world. |
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to speed up inference latency have shown performance degradation caused by a state copying mechanism or numerous exit paths. |
| Approach: | They propose a framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token. |
| Outcome: | The proposed framework outperforms existing frameworks on extensive generation tasks. |
Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models have been fine-tuned for various NLP tasks . prompt tuning is a method that optimizes the output of the model to adapt to downstream tasks based on the posterior distribution of the source task. |
| Approach: | They propose a Bayesian approach to prompt tuning that optimizes for adapting pre-trained language models to downstream tasks rather than fine-tuning full model parameters. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods on benchmark NLP tasks. |
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has shown promising transferability of pre-trained multilingual language models. |
| Approach: | They propose a cross-lingual fine-tuning algorithm that uses SupCon and MixUp to combine them to improve performance. |
| Outcome: | The proposed algorithm improves cross-lingual transferability by using SupCon and MixUp. |
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to align Large Language Models with human preferences fail to maintain general knowledge and alignment when faced with personalized preferences. |
| Approach: | They propose a method that utilizes the initial responses of the reference model to mitigate forgetting while accommodating personalized alignment. |
| Outcome: | The proposed approach mitigates forgetting while accommodating personalized alignment while preserving global knowledge and general alignment. |
Stable Language Model Pre-training by Reducing Embedding Variability (2024.emnlp-main)
Copied to clipboard
| Challenge: | Stable pre-training is essential for achieving better-performing language models, but tracking pre-train stability is impractical due to high computational costs. |
| Approach: | They propose to use Token Embedding Variability as a proxy to estimate pre-training stability. |
| Outcome: | The proposed method improves stability and lowers perplexities even at deeper layer counts. |