Papers by Yuxin He

12 papers
SetGNER: General Named Entity Recognition as Entity Set Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is a fundamental task in the field of information extraction and has played an important role in the development of natural language processing.
Approach: They propose a method that treats each entity as a sequence and is capable of recognizing discontinuous mentions.
Outcome: The proposed model outperforms state-of-the-art generative NER models on two discontinuous NER datasets, two nested NER and one flat NER.
Generative Models for Automatic Medical Decision Rule Extraction from Text (2024.emnlp-main)

Copied to clipboard

Challenge: Medical decision rules are traditionally constructed by medical experts, which is expensive and hard to scale up.
Approach: They propose to extract medical decision rules from text using generative models . their code will be open-source upon acceptance .
Outcome: The proposed model outperforms state-of-the-art models on a Chinese benchmark and achieves 67% tree accuracy.
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Copied to clipboard

Challenge: Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach: They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome: The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models.
Approach: They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories .
Outcome: The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification.
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training (2024.acl-long)

Copied to clipboard

Challenge: Large language models suffer from severe hallucinations, compromising performance in knowledge-oriented QA, dialogue, and writing.
Approach: They propose to enhance the information searching and reflection ability of large language models by training them in position-agnostic multi-step QA tasks to improve their model's accuracy.
Outcome: The proposed model improves in multi-doc QA and other benchmarks by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task.
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Large reasoning models have demonstrated remarkable mathematical problem-solving abilities, but their true reasoning shortcomings are often hidden.
Approach: They propose to leverage the rigor and methodological complexity of mathematical proofs as a diagnostic tool to expose hidden failures.
Outcome: The proposed model evaluation exploits the rigor and complexity of proof problems to uncover 10 fine-grained errors.
BiSPN: Generating Entity Set and Relation Set Coherently in One Pass (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to extract entities and relation triples from text are limited.
Approach: They propose a bipartite set prediction network to generate entity set and relation set in parallel.
Outcome: The proposed model can generate entity set and relation set in parallel, while maintaining coherence between the predicted entities and relation sets.
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)

Copied to clipboard

Challenge: Current development practices face a dichotomy between automation and performance.
Approach: They propose a framework to empower LLMs with the capability of automated explicit vectorization.
Outcome: The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench.
Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences? (2023.acl-long)

Copied to clipboard

Challenge: Recent studies on event argument extraction (EAE) have not taken event co-occurrences into account.
Approach: They propose to reformulate event co-occurrences as a problem of table generation and extend a SOTA prompt-based EAE model into a non-autoregressive generation framework that extracts the arguments of multiple events in parallel.
Outcome: The proposed framework can extract arguments of multiple events in parallel.
IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches fail to integrate domain expert insights beyond simple prompting.
Approach: They propose a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors.
Outcome: Experiments show that IDEA outperforms DeepSeek R1 and GPT-5.2 in accuracy and accuracy.
Safety Alignment via Constrained Knowledge Unlearning (2025.acl-long)

Copied to clipboard

Challenge: Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs.
Approach: They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information.
Outcome: The proposed method significantly improves model safety while maintaining utility compared to existing methods.
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for efficient deployment of small language models face inefficient bit-width allocation and insufficient fine-grained quantization adjustments.
Approach: They propose a weight quantization technique that facilitates efficient deployment of SLMs . they propose to combine inter-layer loss and intra-layer salience to achieve better allocation .
Outcome: Experimental results show that multi-level weight quantization achieves competitive performance compared to state-of-the-art methods.

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