Papers by Yan Cong

9 papers
Cool-Fusion: Fuse Large Language Models without Training (2025.acl-long)

Copied to clipboard

Challenge: Cool-Fusion is a simple yet effective approach to combine two or more heterogeneous large language models .
Approach: They propose a method that fuses the knowledge of two or more heterogeneous large language models to leverage complementary strengths.
Outcome: The proposed method increases accuracy from three strong source LLMs on GSM8K by 17.4%.
Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets (2024.lrec-main)

Copied to clipboard

Challenge: Distributional Semantics has undergone significant changes with the introduction of contextualized distributional models.
Approach: They compare static and contextual distributional models for Mandarin Chinese . they find that static models are stronger for some of the classical tasks .
Outcome: The proposed models perform better on some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and categorization of words into abstract semantic classes.
Exploring the Semantic Space of Second Language Learners (2026.eacl-srw)

Copied to clipboard

Challenge: Using machine learning models, we compared the semantic space of university-level students learning French with native speakers' (L1) .
Approach: They extracted semantic features from narrative text and used interpretability techniques to identify the most informative features per model.
Outcome: The results show that the second language learners had higher semantic similarity scores than the native speakers at the token level, whereas the similarity decreased over time but did not reach native-level values.
Thinking Before You Speak: A Proactive Test-time Scaling Approach (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models often exhibit deficiencies with complex reasoning tasks, such as maths, due to the discrepancy between human reasoning patterns and those presented in training data.
Approach: They propose to insert insights between consecutive reasoning steps to bridge this gap by generating insights between the next reasoning steps.
Outcome: Experiments on mathematical datasets confirm the effectiveness of the proposed reasoning framework on complex problems.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Challenge: Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach: They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome: The proposed framework improves performance of commercial and open-source models.
AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor.
Approach: They propose a reward-based generalizable reward model to guide the policy model for effective test-time search.
Outcome: The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average.
Are Language Models Sensitive to Semantic Attraction? A Study on Surprisal (2023.starsem-1)

Copied to clipboard

Challenge: In psycholinguistics, semantic attraction is a sentence processing phenomenon in which a given argument violates the selectional requirements of a verb but is not perceived by comprehenders due to its attraction to another noun in the same sentence.
Approach: They used autoregressive language models to compute the sentence-level and target phrase-level Surprisal scores of a psycholinguistic dataset on semantic attraction.
Outcome: The proposed models are sensitive to semantic attraction, leading to reduced Surprisal scores, although none perfectly matches the human behavioral pattern.
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for movie dubbing break phonemes in scripts, resulting in incomplete phoneme pronunciation and poor identity stability.
Approach: They propose a method that switches dubbing learning from frame level to phoneme level . it uses a multimodal style adaptor to learn pronunciation style from audio .
Outcome: The proposed method improves on two benchmarks, V2C and Grid, and is available on github.
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach: They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome: The proposed system outperforms baselines in the open domain task-solving benchmark.

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