Papers by Yahui Liu

8 papers
What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in reasoning with large language models have popularized Long Chain-of-Thought (LCoT) a framework that converts sequential LCoTs into hierarchical tree structures enables deeper structural analysis of LLM reasoning.
Approach: They propose a framework that converts sequential LCoTs into hierarchical tree structures and enables deeper structural analysis of LLM reasoning.
Outcome: The proposed framework can be used to analyze LLM reasoning in a variety of tasks and models.
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)

Copied to clipboard

Challenge: Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness.
Approach: They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem.
Outcome: FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments.
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks and evaluation protocols suffer from inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes.
Approach: They propose an automatic framework which leverages Monte Carlo Tree Search to construct numerous and diverse descriptive sentences that thoroughly represent video content in an iterative way.
Outcome: The proposed framework improves MCTS-VCB and DREAM-1K on video captioning tasks by 25.0% and 16.3% respectively.
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method (D18-1)

Copied to clipboard

Challenge: Experimental results show that Sequence-to-sequence models tend to generate generic/dull responses .
Approach: They propose a statistical re-weighting method that assigns different weights for multiple responses of the same query.
Outcome: The proposed method improves acceptance rate of generated responses and significantly reduces generated generic responses.
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics (2022.findings-acl)

Copied to clipboard

Challenge: Current evaluation methods focus on one dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task.
Approach: They propose to use a single dataset to evaluate the performance of automatic translation metrics.
Outcome: The results show that the rankings of metrics vary when the evaluation is conducted on different datasets.
Assessing Dialogue Systems with Distribution Distances (2021.findings-acl)

Copied to clipboard

Challenge: Existing evaluation metrics focus on turnlevel quality, which is not well suited for open-end dialogue tasks.
Approach: They propose to measure the performance of a dialogue system by computing the distributionwise distance between its generated conversations and real-world conversations.
Outcome: The proposed metrics correlate better with human judgments than existing metrics on dialogue systems.
MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies show that shallow semantic role labeling (SRL) performance drops under out-of-domain setting.
Approach: They propose to annotate a multi-domain Chinese predicate-argument dataset using a frame-free annotation methodology and strict double annotation for improving data quality.
Outcome: The proposed dataset is compared with a dataset from six different domains.
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity.
Approach: They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation.
Outcome: The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories.

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