Papers by Linjuan Wu

11 papers
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach: They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome: Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach: They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome: The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to zero-shot transfer knowledge from rich-resource to low-resourced languages are limited due to linguistic discrepancies in different languages.
Approach: They propose a multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model to disassociate semantics from syntax in models learned by multilingual pre-trained models.
Outcome: The proposed model disassociates semantics from syntax in multilingual models.
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Challenge: Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach: They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome: The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.
Good Meta-tasks Make A Better Cross-lingual Meta-transfer Learning for Low-resource Languages (2023.findings-emnlp)

Copied to clipboard

Challenge: Model-agnostic meta-learning has garnered attention as a promising technique for enhancing few-shot cross-lingual transfer learning in low-resource scenarios.
Approach: They propose a Meta-Task Collector-based Cross-lingual Meta-Transfer framework to adapt data selection strategies to construct cross-lingual meta-tasks to reduce language gaps.
Outcome: The proposed framework significantly improves model performance in the target language with minimal annotation costs.
Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing cross-lingual transfer are limited by parallel resources and lack linguistic and domain coverage.
Approach: They propose a cross-lingual in-context pre-training approach that leverages semantically related bilingual Wikipedia documents to enhance cross-linguistic transfer.
Outcome: The proposed approach improves multilingual performance on three models across six target languages.
From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction Tuning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) acquire strong language skills through extensive pre-training and supervised fine-tuning (SFT) on instructionresponse pairs.
Approach: They propose a method which leverages translation-based parallel instruction data to enhance cross-lingual adaptability.
Outcome: The proposed model improves on Llama-2-7B across five languages against three objective benchmarks and an LLM-as-a-judge benchmark.
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives (2024.acl-long)

Copied to clipboard

Challenge: Recent research indicates without external feedback, LLM’s intrinsic reflection is unstable.
Approach: They propose a method that combines self-evaluated and external feedback to improve LLM's reflection.
Outcome: The proposed method improves the quality of self-evaluated feedback and can catalyze more accurate and stable reflection.
Struct-XLM: A Structure Discovery Multilingual Language Model for Enhancing Cross-lingual Transfer through Reinforcement Learning (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods require syntactic labels that are difficult to obtain and of poor quality for low-resource languages.
Approach: They propose a syntactic alignment model that leverages reinforcement learning to discover universal syntaktic structures for cross-lingual PLM alignment.
Outcome: The proposed model improves cross-lingual representation alignment on the XTREME benchmark.
AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing automated approaches operate within fixed task schemas and often fail to autonomously discover new evaluation dimensions.
Approach: They propose an automated framework that constructs domain-specific benchmarks directly from unstructured corpora using Bloom’s Taxonomy.
Outcome: The proposed framework uncovers a broader and more fine-grained task space than expert-curated benchmarks while producing high-quality instances that preserve established model-level evaluation trends.
TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models’ Theory-of-Mind (2024.findings-acl)

Copied to clipboard

Challenge: Theory of Mind (ToM) is the foundation of social interaction and is crucial for social interaction.
Approach: They propose a tool-belief solver that can transform a character’s higher-order beliefs into another character’ s first-order belief under belief communication period.
Outcome: The proposed model improves the ToM capabilities of Large Language Models (LLMs) in multiple scenarios.

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