Papers by Weijie Yu

12 papers
Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing legal mathematical reasoning models lack structured numerical reasoning . existing models perform poorly on LexNum, while LexPam improves both mathematical accuracy and legal coherence.
Approach: They propose a legal mathematical reasoning benchmark LexNum and LexPam to address this problem . LexPam is a two-stage reinforcement learning framework for efficient legal reasoning training.
Outcome: The proposed framework improves mathematical accuracy and legal coherence . it also improves legal cohesion and generalizes effectively across tasks and domains.
Topology-of-Question-Decomposition: Enhancing Large Language Models with Information Retrieval for Knowledge-Intensive Tasks (2025.coling-main)

Copied to clipboard

Challenge: Large language models (LLMs) are constrained to chaining immediate reasoning steps and relying solely on parametric knowledge.
Approach: They propose a framework that activates retrieval only when necessary to improve answer accuracy.
Outcome: Experiments show that the proposed framework improves performance in knowledge-intensive tasks.
Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Recent work studies RLVR through token entropy, arguing that high-entropies drive exploration and should receive stronger updates.
Approach: They propose a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments.
Outcome: The proposed framework improves accuracy over strong RL baselines across three backbones and six math benchmarks while maintaining high-entropy exploration.
MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment (2025.acl-long)

Copied to clipboard

Challenge: Existing personalized product search methods assume that users’ query fully captures their real motivation, but in practice, user's queries do not always articulate the requirements.
Approach: They propose a Motivation-Aware Personalized Search method that embeds queries and consultations into a unified semantic space via LLMs and utilizes a Mixture of Attention Experts (MoAE) to prioritize critical semantics.
Outcome: Extensive experiments on real and synthetic data show that the proposed method outperforms existing methods in retrieval and ranking tasks.
Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Current legal large language models lack trichotomous reasoning capabilities due to the absence of an appropriate benchmark dataset.
Approach: They propose a benchmark dataset for Legal Judgment Prediction with Innocent Verdicts that incorporates trichotomous dogmatics into zero-shot prompting and fine-tuning.
Outcome: The proposed dataset extends three widely-used legal datasets through LLM-based augmentation and manual verification.
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains (2020.emnlp-main)

Copied to clipboard

Challenge: Asymmetrical text matching is a fundamental problem in information retrieval and natural language processing.
Approach: They propose a method that regularizes features vectors projected from different domains . WD-Match can be used to improve different text matching methods .
Outcome: The proposed method outperforms existing methods and benchmarks on four datasets.
Logic Rules as Explanations for Legal Case Retrieval (2024.lrec-main)

Copied to clipboard

Challenge: Recent efforts to learn explainable legal case retrieval models fail to provide faithful and interpretable explanations for legal cases.
Approach: They propose a framework that uses logic rules to explain legal case retrieval results . they extend benchmarks of LeCaRD and ELAM with manually annotated logic rules .
Outcome: The proposed framework is able to provide faithful explanations for legal case retrieval.
CitaLaw: Enhancing LLM with Citations in Legal Domain (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks have focused on enabling large language models (LLMs) to generate citationsupported outputs.
Approach: They propose to use a citation-based framework to evaluate LLMs' ability to produce legally sound responses with appropriate citations.
Outcome: The proposed framework enables LLMs to retrieve supporting citations from the reference corpus and align these citation with the corresponding sentences in their responses.
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for document matching are limited by the partial nature of the sentence-level matching signals.
Approach: They propose a matching approach that equips existing document matching models with an Optimal Partial Transport component, namely OPT-Match, which selects the key sentences that play a major role in matching.
Outcome: The proposed approach outperforms existing models on four publicly available datasets and the key sentences selected by it are consistent with human-provided rationales.
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Parity LLM Data Valuation (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance.
Approach: They propose a third-party data valuation approach that assesses the value of individual data samples and proposes a learning strategy to approximate LinFiK.
Outcome: The proposed approach surpasses baselines in effectiveness and efficiency, showing significant scalability advantages as LLM parameters increase.
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Personalization can inadvertently distort factual reasoning when faced with factual queries.
Approach: They propose a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior.
Outcome: Experiments across multiple LLM backbones and personalization methods show that FPPS significantly improves factual accuracy while maintaining personalized performance.
Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but this lacks exploration of needs in user consultations.
Approach: They propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value.
Outcome: The proposed model outperforms baselines on public and commercial datasets on both retrieval and ranking tasks.

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