Papers by Yangyifan Xu

6 papers
LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs (2025.acl-long)

Copied to clipboard

Challenge: Long-context modeling has drawn more attention in the area of Large Language Models (LLMs).
Approach: They propose a Long-context data selection framework with Attention-based Dependency Measurement which can efficiently identify high-quality long-contrast data from a large-scale, multi-domain pre-training corpus.
Outcome: The proposed framework significantly boosts the performance of LLMs on multiple long-context tasks with only 1B tokens for continual training.
Collaborative Beam Search: Enhancing LLM Reasoning via Collective Consensus (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve the reasoning capabilities of large language models (LLMs) depend on domain-specific external verifiers or self-evaluation which is brittle and prompt-sensitive.
Approach: They propose a framework that harnesses the collective intelligence of multiple large language models across both generation and verification stages.
Outcome: The proposed framework outperforms singlemodel scaling and multi-model ensemble baselines on six tasks by over 4 percentage points in average accuracy.
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation (2021.acl-short)

Copied to clipboard

Challenge: Existing approaches to token-level adaptive training only use static word frequency information without considering the source language.
Approach: They propose a bilingual mutual information based adaptive objective that assigns weights to target tokens with higher BMI . they propose to use this approach to improve token-level adaptive training .
Outcome: The proposed method improves token-level adaptive training on two languages.
Hit the Sweet Spot! Span-Level Ensemble for Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: a recent study focused on sample-level and token-level ensembles, which hinder dynamic correction and enhancement of outputs during the generation process.
Approach: They propose a span-level ensemble method that balances real-time adjustments and accurate ensemble decisions.
Outcome: The proposed method improves performance across language generation tasks significantly.
Bridging the Gap between Different Vocabularies for LLM Ensemble (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods to combine large language models with complete outputs have limited effectiveness . lexical gaps between different LLMs hinder dynamic correction and enhancement .
Approach: They propose a method to ensemble large language models via Vocabulary Alignment (EVA) they learn mappings between vocabularies of different LLMs with overlapping tokens .
Outcome: The proposed method bridges the lexical gap among various LLMs, enabling meticulous ensemble at each generation step.
Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive performance across numerous NLP tasks, but fine-tuning them for Machine Translation (MT) often introduces catastrophic forgetting, compromising the broad general abilities of LLMs and introducing potential security risks.
Approach: They propose a method that harnesses the strong generative capabilities of Large Language Models to create rationales for training data, which are then "replayed" to prevent forgetting.
Outcome: The proposed approach harnesses the strong generative capabilities of LLMs to create rationales for training data, which are then “replayed” to prevent forgetting.

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