Papers by Xingyuan Li

10 papers
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings (2020.emnlp-main)

Copied to clipboard

Challenge: Multi-Word Expressions (MWEs) are common in every language, but they are not translated by cross-lingual word embeddings.
Approach: They propose a method for word translation of Multi-Word Expressions (MWEs) they compile lists of MWEs in each language and tokenize them as single tokens before training word embeddings.
Outcome: The proposed method can translate multi-word expressions to and from English in 10 languages.
Phonetic and Lexical Discovery of Canine Vocalization (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to study animal language systems rely on human prior knowledge on limited data.
Approach: They propose a self-supervised approach that enables the accurate classification of phones and an adaptive grammar induction method that identifies phone sequence patterns that suggest a preliminary vocabulary within dog vocalizations.
Outcome: The proposed approach breaks the barrier existing approaches relying on human prior knowledge on limited data.
Toward Automatic Discovery of a Canine Phonetic Alphabet (2025.acl-long)

Copied to clipboard

Challenge: a new algorithm for vocalization communication between dogs is being developed . phonetic units alone are not sufficient to constitute a "language"
Approach: They propose an algorithm that produces a complete alphabet of distinct canine phonemes . the algorithm is expected to function on canines and other animal species .
Outcome: The proposed algorithm produces a complete alphabet of distinct canine phoneme-like units . it is expected to work on canines and other animal species .
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences.
Approach: They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects.
Outcome: The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives.
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Challenge: Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach: They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome: The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach: They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome: The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence.
Approach: They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics .
Outcome: The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate .
Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for learning from weakly-supervised speech data are hampered by severe data scarcity and the subjective nature of clinical annotations.
Approach: They propose a framework that explicitly models pathological traits by jointly learning from frame-level, segment-level and session-level representations within unsegmented clinical dialogues.
Outcome: The proposed framework is model-agnostic, robust across languages and conditions, and highly data-efficient.
GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing models for long contexts struggle to handle long inputs due to limited context window and memory usage.
Approach: They propose a graph-based agent system that analyzes long texts into a graphical graph . GraphReader consistently outperforms GPT-4-128k across context lengths from 16k to 256k .
Outcome: The proposed model outperforms existing models on four challenging benchmarks.
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in o1-like models have generated long Chain-of-Thought reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs).
Approach: They propose a DeltaBench to analyze the quality and effectiveness of o1-like models and measure their ability to detect errors in long COT reasoning.
Outcome: The proposed model can detect errors in long COT reasoning.

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