Papers by Yujie Wu

15 papers
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.acl-long)

Copied to clipboard

Challenge: Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting.
Approach: They propose a framework that aligns replay schedules with a model-centric notion of time.
Outcome: Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting.
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for hallucination evaluation rely on mixed queries and posterior evaluation, which quantifies hallucinosity severity but offers limited insight into where and why they occur.
Approach: They propose a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors.
Outcome: The proposed model disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors.
Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies use legal facts to predict judgments, but legal facts are difficult to obtain in early stages of litigation.
Approach: They propose a legal fact prediction task that takes evidence from trial as input to make predictions in the absence of ground-truth legal facts.
Outcome: The proposed task can predict court rulings without ground-truth legal facts . the first benchmark dataset, LFPBench, is used to evaluate the task .
Continual Dialogue State Tracking via Reason-of-Select Distillation (2024.findings-acl)

Copied to clipboard

Challenge: Existing research on dialogue systems has focused on domain-specific offline systems lacking adaptation abilities.
Approach: They propose a Reason-of-Select distillation method that enhances smaller models with a novel "meta-reasoning" capability.
Outcome: Experiments show that the proposed method significantly improves the performance and generalization capabilities of existing models.
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning (2025.acl-long)

Copied to clipboard

Challenge: Continual learning (CL) is crucial for large language models without costly retraining.
Approach: They propose a framework for recurrent knowledge identification and fusion that enables dynamic estimation of parameter importance distributions to enhance knowledge transfer.
Outcome: The proposed framework mitigates catastrophic forgetting and enhances knowledge transfer.
BMAM: Brain-inspired Multi-Agent Memory Framework (2026.findings-acl)

Copied to clipboard

Challenge: Language-model-based agents operating over extended interactions face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions.
Approach: They propose a general-purpose memory architecture that decomposes agent memory into six components that operate at complementary time scales.
Outcome: BMAM outperforms memory-augmented baselines on LoCoMo benchmarks with 78.45% accuracy . a targeted refinement of the temporal-trigger heuristics raises LongMemEval multi-session accuracy from 45.2% to 56.4%.
RAP-ID: Mechanistic Prompt Injection Detection via Impostor Behavior Analysis (2026.findings-acl)

Copied to clipboard

Challenge: Existing defenses rely on externally deployed guardrail models or response inspection . current defenses depend on external guardrails or response inspecting .
Approach: They propose a mechanistic, train-free detection framework that operates exclusively on internal state dynamics during the initial forward pass.
Outcome: The proposed framework achieves competitive performance with significant overall improvements compared to heuristic methods.
Towards LLM-driven Dialogue State Tracking (2023.emnlp-main)

Copied to clipboard

Challenge: emergence of large language models (LLMs) such as GPT3 and ChatGPT has sparked considerable interest in assessing their efficacy across diverse applications.
Approach: They present a framework for a domain-slot instruction tuning method that allows LDST to achieve performance on par with ChatGPT.
Outcome: The proposed framework performs better in zero-shot and few-shot settings than previous SOTA methods.
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation (2024.acl-long)

Copied to clipboard

Challenge: Current methods for Continual Dialogue State Tracking (DST) struggle with catastrophic forgetting and knowledge transfer between tasks.
Approach: They propose a framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay.
Outcome: The proposed framework shows a 7.6% increase in Avg. JGA and 11% rise in BWT metrics over existing state-of-the-art methods.
GeoEdit: Geometric Knowledge Editing for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing training-based model editing methods struggle to incorporate new knowledge while preserving unrelated general knowledge.
Approach: They propose a framework that uses geometric relationships to differentiate between neurons associated with new knowledge updates and those related to general knowledge perturbations.
Outcome: The proposed framework avoids updating neurons with directions approximately orthogonal to existing knowledge, thus preserving the model’s generalization ability.
MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for open relation extraction (OpenRE) focus on labeled and pre-defined instances, which are costly to acquire in reality.
Approach: They propose a framework that can extract relations without pre-defined types from open-domain corpus with efficient knowledge transfer from a few pre-determined relational instances.
Outcome: The proposed framework achieves the new SOTA results for OpenRE on different datasets.
How Good Are LLMs at Out-of-Distribution Detection? (2024.lrec-main)

Copied to clipboard

Challenge: Out-of-distribution (OOD) detection is crucial for ensuring AI safety . large language models (LLMs) are becoming more prevalent due to their scale, pre-training objectives, and paradigms used for inference.
Approach: They propose to use large language models to investigate out-of-distribution (OOD) detection in machine learning.
Outcome: The proposed method outperforms other OOD detectors in zero-grad and fine-tuning scenarios.
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent model merging-based methods struggle to effectively manage the trade-off between learning new knowledge and preventing catastrophic forgetting.
Approach: They propose a model merging framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model’s training status.
Outcome: The proposed framework achieves significant performance improvements over existing state-of-the-art methods on three CL benchmarks with various model sizes (from 770M to 13B).
Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Open Domain Multi-Hop Question Answering (ODMHQA) is one of the most challenging tasks in Natural Language Processing (NLP)
Approach: They propose a mechanism that leverages the intrinsic capabilities of Large Language Models to judge whether the generated answers are off-topic.
Outcome: The proposed method reduces the occurrence of off-topic answers by nearly 13%, improving the performance in Exact Match (EM) by nearly 3% compared to the baseline method without the Dr3 mechanism.
Zero-shot Cross-domain Dialogue State Tracking via Context-aware Auto-prompting and Instruction-following Contrastive Decoding (2024.emnlp-main)

Copied to clipboard

Challenge: Previous studies have implemented slot-based input improvements, such as schema-driven descriptions and question-answering formats, but still suffer from negative transfer for seen slots and inefficient transfer for unseen slots due to the significant source-target domain gap.
Approach: They propose a framework that generates dynamic, context-aware slot queries to improve model transferability by penalizing deviations from the provided instructions.
Outcome: Experiments on two datasets show that the proposed model performs better than existing models on the restaurant domain.

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