Papers by Yun Hong

9 papers
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

Copied to clipboard

Challenge: Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach: They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome: The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.
Who Wrote this Code? Watermarking for Code Generation (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to detect machine-generated text by embedding watermarks fail to function appropriately in code generation tasks due to the task’s nature of having low entropy.
Approach: They propose a logit-modifying watermark method which enhances detection ability and mitigates code quality degeneration by removing low-entropy segments at generating and detecting watermarks.
Outcome: The proposed method outperforms baseline methods in detecting machine-generated code text while preserving code quality.
Efficient Training for Cross-lingual Speech Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Currently, large language models (LLMs) focus on the text modality, making speech modeling difficult.
Approach: They propose a cross-lingual speech language model that trains on discrete speech tokens to achieve cross-modal and cross-linguistic alignment through continual pre-training.
Outcome: The proposed method achieves cross-modal and cross-lingual alignment through continual pre-training.
M³GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering Benchmark (2025.acl-long)

Copied to clipboard

Challenge: GraphRAG systems have achieved remarkable progress in enhancing performance and reliability of large language models.
Approach: They propose a GraphRAG benchmark focusing on multi-entity queries with six settings for comprehensive evaluation.
Outcome: The proposed method can construct diverse data with semantically correct ground-truth reasoning paths.
MANTA: A Scalable Pipeline for Transmuting Massive Web Corpora into Instruction Datasets (2025.findings-emnlp)

Copied to clipboard

Challenge: MANTA-1M generates high-quality large-scale instruction fine-tuning datasets from web corpora . scalability and diversity of the datasets are preserved, allowing expansion into domains requiring intensive knowledge.
Approach: a team of researchers introduce a pipeline that fine-tunes large-scale instruction datasets from web corpora with minimal human intervention.
Outcome: MANTA generates high-quality large-scale instruction fine-tuning datasets from web corpora . leveraging high-performance LLMs, MANTE outperforms other methods in knowledge-intensive tasks .
FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, but struggle with tasks requiring simultaneous retrieval of multiple facts.
Approach: They propose a method that refines context through successive rounds of rewriting to address this problem by finding all Crucial Texts (FACT)
Outcome: The proposed method improves multi-fact retrieval performance across tasks, though improvements are less notable in general-purpose QA scenarios.
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.
FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Recent research has made significant progress in developing empathetic spoken chatbots based on large language models (LLMs).
Approach: They propose an end-to-end empathetic spoken chatbot trained efficiently that generates emotionally expressive speech and outperforms other emmpathetic models in emphatic dialogue, SER, and SpokenQA tasks.
Outcome: The proposed model outperforms other empathetic models on e-dialog, SER, and SpokenQA tasks and achieves strong results on several speech tasks.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations