Papers by Liangyou Li

20 papers
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training (2021.emnlp-main)

Copied to clipboard

Challenge: MultiUAT dynamically adjusts training data usage based on model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Approach: They propose an approach that dynamically adjusts the training data usage based on the model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Outcome: The proposed approach outperforms baselines on 16 languages and 2 domains on English-German translation.
Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing (2025.acl-long)

Copied to clipboard

Challenge: Existing studies to improve mathematical ability typically involve applying preference learning to step-wise solution pairs, but they overlook critical subtle errors.
Approach: They propose a preference learning framework that injects predefined subtle errors into pivotal tokens to construct hard pairs for error mitigation.
Outcome: Extensive experiments show that the proposed framework improves on Qwen2-7B-Instruct and MATH with 4.5K training samples.
Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Challenge: Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach: They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome: The proposed approach yields consistent improvements over strong competitors for multiple translation directions.
FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models (2022.findings-naacl)

Copied to clipboard

Challenge: Existing work on cross-lingual transfer has not studied how to leverage knowledge of rich-resource languages without labels.
Approach: They propose a 2-step knowledge distillation framework to achieve knowledge transfer from off-the-shelf models in rich-resource languages.
Outcome: The proposed method reduces annotation cost and protects private labels.
SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods of generating singable lyrics are based on a given melody, but there are two main challenges: generating the lyrics without knowing the melody and composing compatible melodies.
Approach: They propose a Chinese lyric generation and editing system which rewrites lyrics of an existing song such that they are compatible with the rhythm of the existing melody.
Outcome: The proposed system is based on a randomized multi-level masking strategy and can generate new lyrics or edit fragments without prior knowledge of melody composition.
Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods that use Chain-of-Thought suffer from path homogenization and inefficient use of intermediate results.
Approach: They propose a framework that introduces checkpoints between reasoning steps to reduce path homogenization and create fault-tolerant mechanisms.
Outcome: The proposed framework reduces path homogenization and creates fault-tolerant mechanism by utilizing high-quality intermediate results.
AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation (2023.findings-emnlp)

Copied to clipboard

Challenge: End-to-end speech translation (ST) models need large amount of training data to perform well.
Approach: They propose a shrinking mechanism to mitigate the length mismatch between speech and text features by predicting word boundaries.
Outcome: The proposed method achieves better performance on the MUST-C dataset, with higher inference speed and lower memory usage.
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge (2025.acl-long)

Copied to clipboard

Challenge: Existing methods rely on majority voting or criteria expansion to capture detailed and detailed details, often leading to incomplete outcomes.
Approach: They propose a method which introduces additional crowd responses to compare with the candidate responses, thereby exposing deeper and more comprehensive details within the candidate answers.
Outcome: Experiments show that the proposed method improves evaluation reliability and achieves an average gain of 6.7% across five benchmarks.
RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer (2021.findings-acl)

Copied to clipboard

Challenge: End-to-end simultaneous speech translation (SST) is useful in many scenarios but has not been fully investigated.
Approach: They propose an end-to-end simultaneous speech translation model called RealTranS . they use interleaved convolution and unidirectional Transformer layers to downsample input speech .
Outcome: The proposed model outperforms existing models on public and widely-used datasets in multiple latency settings.
Universal Conditional Masked Language Pre-training for Neural Machine Translation (2022.acl-long)

Copied to clipboard

Challenge: Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT) this paper demonstrates that pre-training a sequence- to-squence model with a bidirectional decoder can produce notable performance gains for both Autoregressive and Non-autoregressive NMT tasks.
Approach: They propose a conditional masked language model pre-trained on bilingual and monolingual corpora in many languages.
Outcome: The proposed model can achieve significant performance improvements on all scenarios from low- to extremely high-resource languages.
Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Copied to clipboard

Challenge: Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach: They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome: The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.
Triangular Transfer: Freezing the Pivot for Triangular Machine Translation (2022.acl-short)

Copied to clipboard

Challenge: Existing approaches to triangular machine translation have not fully exploited all types of auxiliary data.
Approach: They propose a transfer-learning-based approach that utilizes all types of auxiliary data.
Outcome: The proposed approach outperforms existing approaches with a series of experiments.
NILE: Internal Consistency Alignment in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances show that the world knowledge in the Instruction Fine-Tuning (IFT) dataset, which is incompatible with LLMs’ internal knowledge, can greatly hurt the IFT performance.
Approach: They propose a framework to optimize the effectiveness of IFT by carefully aligning the world and internal knowledge of LLMs.
Outcome: The proposed framework can significantly improve performance across multiple LLM ability evaluation datasets.
ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) can be enhanced by using supervised fine-tuning . however, access to fine-timing data can be limited.
Approach: They propose a Graph-based Sampling strategy and a Planned-generation strategy to enhance the coherence between dialogues by using 8,000 synthetic dialogues.
Outcome: The proposed model achieves tool-calling performance comparable to or surpassing GPT-4 while maintaining strong general capabilities.
Document Graph for Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing document-level NMT methods fail to leverage contexts beyond a few set of previous sentences.
Approach: They propose to represent a document as a graph that connects relevant contexts regardless of distances.
Outcome: Experiments on IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian show that using document graphs can significantly improve translation quality.
FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction.
Approach: They propose a Multi-level Fine-grained Constraints Following Benchmark for Large Language Models that adds a single constraint to the initial instruction at each increased level.
Outcome: The proposed model can follow instructions with more constraints, and is deemed to have better instruction-following ability.
Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step (2025.findings-naacl)

Copied to clipboard

Challenge: Current research found the issue of Early Answering in large language models where the models already have an answer before generating the Chain-of-Thought (CoT).
Approach: They propose a method to probe changes in confidence during the model’s reasoning and prioritize answers with correct reasoning among multiple candidates.
Outcome: The proposed method reveals that in a significant number of question-answer cases, CoT appears to be unnecessary and this necessity correlates with the simplicity of the task, defined by the reasoning steps required.
Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning open-source LLMs are limited to text-based analysis under predefined general criteria.
Approach: They propose a framework that fine-tunes LLMs to replicate the evaluation explanations and judgments of proprietary models.
Outcome: The proposed evaluation framework outperforms existing fine-tuned evaluation methods in effectiveness and robustness.
A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation (2020.aacl-main)

Copied to clipboard

Challenge: Despite the success of neural machine translation, simultaneous neural machine translators are challenging due to syntactic structure difference and simultaneity requirements.
Approach: They propose a framework for adapting neural machine translation to translate simultaneously . they propose 'prefix translation' that utilizes a consecutive NMT model to translate source prefixes .
Outcome: The proposed framework balancing quality and latency on three translation corpora and two language pairs shows that it performs well.
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation frameworks focus on single-turn evaluations, overlooking the models’ capabilities in multi-turn interactions.
Approach: They propose a benchmark to evaluate the multi-turn conversational abilities of large language models (LLMs) by analyzing human-LLM conversations and constructing multi-turned queries for each category using GPT-4.
Outcome: The proposed model outperforms open-source models in multi-turn tasks while retaining and recalling historical information.

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