Papers by Zelin Li

12 papers
Reward Alignment Optimization: A Direct Point-wise Alignment Approach (2026.acl-long)

Copied to clipboard

Challenge: Existing Direct Alignment Algorithms (DAAs) are limiting in generalizaiton to implicit rewards.
Approach: They propose a point-wise direct alignment method that uses an explicit reward model to specify exact target generation probabilities and align the policy offline towards them.
Outcome: The proposed method outperforms existing direct alignment algorithms while enabling controllable target probability distributions.
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making (2021.acl-long)

Copied to clipboard

Challenge: Entity Matching (EM) aims at recognizing entity records that denote the same real-world object.
Approach: They propose a novel EM framework that consists of Heterogeneous Information Fusion and Key Attribute Tree Induction to decouple feature representation from matching decision.
Outcome: The proposed framework outperforms SOTA EM models on 6 public datasets and 3 industrial datasets.
How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing? (2022.findings-acl)

Copied to clipboard

Challenge: Extensive experiments on multi-lingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer.
Approach: They propose to transfer semantic knowledge from rich-resourced languages to low-resource languages by using multilingual transfer learning.
Outcome: The proposed model outperforms baselines and can handle negative transfer.
KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs (2025.coling-main)

Copied to clipboard

Challenge: Existing studies have shown that combining information from KGs in different languages aids knowledge Graph Completion and Knowledge Graph Enhancement.
Approach: They propose a sequence-to-sequence framework that unifies tasks of textual and relational information completion for multilingual knowledge graphs.
Outcome: The proposed framework unifies tasks of KGC and KGE into a single framework.
Do Large Language Models have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs (2025.acl-long)

Copied to clipboard

Challenge: Current Large Language Models (LLMs) are predominantly designed with English as the primary language, but many are still English-dominated.
Approach: They propose to use automatic corpus-level metrics to assess lexical and syntactic naturalness of LLMs in a multilingual context.
Outcome: The proposed method improves naturalness of LLMs in target languages without compromising performance on general-purpose benchmarks.
An LLM-based Framework for Biomedical Terminology Normalization in Social Media via Multi-Agent Collaboration (2025.coling-main)

Copied to clipboard

Challenge: Experimental results indicate that our approach exhibits competitive performance.
Approach: They propose a tuning-free approach to normalize non-standard terms using large language models . they use a search engine and a domain knowledge base to expand the short texts into accurate descriptions .
Outcome: The proposed approach is based on the "Recall and Re-rank" framework . it can be used to identify the standard term in a specified termbase for non-standardized mentions .
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for retrieving historical messages are based on similarity-based mechanisms.
Approach: They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection.
Outcome: The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S.
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for multi-hop reasoning are not able to evaluate their interpretability . a recent study found that many paths are unreasonable .
Approach: They propose a framework to evaluate the interpretability of multi-hop reasoning models . they annotate all possible rules and establish a benchmark .
Outcome: The proposed framework outperforms existing models in terms of performance and interpretability.
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)

Copied to clipboard

Challenge: Current medical benchmarks have limitations in question design, data sources and evaluation methods.
Approach: They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records .
Outcome: The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for multi-hop knowledge graph reasoning suffer from slow and poor convergence . a transformer model can be used to learn and predict in an end-to-end fashion, giving faster convergence compared to previous methods .
Approach: They propose a Sequence-to-sequence based multi-hop reasoning framework . it uses an encoder-decoder transformer structure to translate the query to a path .
Outcome: The proposed framework can learn and predict in an end-to-end fashion, which gives better and faster convergence.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
Expectation Preference Optimization: Reliable Preference Estimation for Improving the Reasoning Capability of Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Pairwise preference optimization is used to improve supervised fine-tuning performance of large language models.
Approach: They propose an algorithm that takes pairs of sample groups instead of single samples for preference learning.
Outcome: The proposed algorithm outperforms baseline methods on reasoning benchmarks.

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