Papers by Kai Song

25 papers
An Empirical Study of Iterative Refinements for Non-autoregressive Translation (2025.acl-long)

Copied to clipboard

Challenge: Iterative non-autoregressive (NAR) models have recently demonstrated impressive performance in varied generation tasks, surpassing the autoregressive Transformer.
Approach: They propose a strategy to conduct efficient refinements without performance declines by using two simple metrics to identify potential problems existing in current refinement processes.
Outcome: The proposed model outperforms the autoregressive Transformer by around one BLEU on average.
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder (2024.findings-naacl)

Copied to clipboard

Challenge: generative diversity is a critical yet underexplored issue in natural language generation . previous approaches to enhance diversity of Transformer models have been limited by their latent variables .
Approach: They propose a framework that bridges Transformer with VAE to enhance generative diversity.
Outcome: The proposed framework improves generative diversity while maintaining generative quality.
A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and Extrapolation (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for temporal knowledge graphs de-emphasize temporal correlations between facts sequences and ignore inferring clues from missing facts.
Approach: They propose a Temporal PAth-based reasoning model that is robust to ambiguous temporal data.
Outcome: The proposed model outperforms SOTA methods on the link prediction task.
Multi-Stage Pre-training for Automated Chinese Essay Scoring (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for automatic essay scoring are based on hand-crafted surface-level features, but recent advances in representation learning have improved performance.
Approach: They propose a pre-training based automated Chinese essay scoring method with weakly supervised pre- training, supervised cross- prompt fine-tuning and supervised target- prompt refine-tuneing.
Outcome: The proposed method improves a state-of-the-art neural essay scorer in terms of effectiveness and domain adaptation ability, while in-depth analysis also reveals its limitations.
MusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completion (2025.emnlp-main)

Copied to clipboard

Challenge: Open-world knowledge graph completion (KGC) aims to infer novel facts by enriching existing graphs with external knowledge sources while maintaining semantic consistency under the open-world assumption (OWA).
Approach: They propose a multi-source knowledge enhancement framework based on an open-world assumption (OWA) that integrates external knowledge sources and a new evaluation strategy to validate new facts.
Outcome: The proposed model achieves SOTA performance across benchmarks and the evaluation strategy effectively assesses new facts under OWA.
UnitCoder: Scalable Code Synthesis from Pre-training Corpora (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel at code understanding and generation, yet code generation remains a challenge.
Approach: They propose a model that supervises pre-training data quality through automatically generated unit tests while ensuring correctness via an iterative fix and refine flow.
Outcome: The proposed model improves performance on a large dataset with high quality pre-training data.
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback (2026.findings-acl)

Copied to clipboard

Challenge: Time series anomaly detection (TSAD) has traditionally focused on binary classification and lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making.
Approach: They propose a time-series reasoning task that reformulates TSAD from discriminative to reasoning-intensive paradigm.
Outcome: The proposed task reformulates TSAD from discriminative to reasoning-intensive paradigm.
Revealing the Parallel Multilingual Learning within Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) can handle multilingual and cross-lingual text within a single input; however, previous studies focusing on using English as the pivot language to enhance language understanding and reasoning focus on using multiple languages.
Approach: They propose to use parallel multilingual input to enhance the model's comprehension of the input and to examine how multilingual processing affects prediction.
Outcome: The proposed model can handle multilingual and cross-lingual text within a single input, but previous studies focused on using English as the pivot language to enhance language understanding and reasoning.
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to conversational Query Reformulation (CQR) suffer from high dependency on external supervision from annotations or large language models and insufficient alignment between the rewriter and downstream retrievers.
Approach: They propose a framework that transforms context-dependent queries into self-contained forms suitable for off-the-shelf retrievers.
Outcome: The proposed framework outperforms existing methods on topiOCQA and QReCC datasets while using smaller 3B parameter models without external supervision.
CAMIEval: Enhancing NLG Evaluation through Multidimensional Comparative Instruction-Following Analysis (2025.naacl-long)

Copied to clipboard

Challenge: Evaluating the quality of texts generated by language models has always been a challenging task in natural language processing (NLP).
Approach: They propose a multidimensional comparative evaluation method based on instruction-following that combines relevance, factuality, and adherence with a concrete Chain-of-Thoughts process to enhance the accuracy of evaluations.
Outcome: The proposed method outperforms existing methods in correlation with human evaluations on two NLG evaluation benchmarks.
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Copied to clipboard

Challenge: GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach: They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome: The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.
Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks explore aspects of threedimensional spatial reasoning and visual-language reasoning in dynamic environments, but they are unable to perform well on 3D spatial deformation reasoning.
Approach: They propose to use a ladder competition format to assess the model's spatial deformation reasoning abilities to determine its performance.
Outcome: The proposed framework assesses the performance of Vision-Language Models in spatial deformation reasoning tasks.
FiNE: Filtering and Improving Noisy Data Elaborately with Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Currently, there are two mainstream methods for improving data integrity: data filtering and data augmentation.
Approach: They propose a method to improve data integrity by combining data filtering and data augmentation with LLMs.
Outcome: The proposed method surpasses the open-source chat version on HalluQA by 8.45 on the open source version.
TextHide: Tackling Data Privacy in Language Understanding Tasks (2020.findings-emnlp)

Copied to clipboard

Challenge: Unsolved privacy challenges in distributed or federated learning are a challenge for many domains including Natural Language Processing.
Approach: They propose a federated learning framework that adds an encryption step to prevent an eavesdropping attacker from recovering private text data.
Outcome: The proposed model can effectively defend against attacks on shared gradients or representations and the averaged accuracy reduction is only 1.9%.
FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models (2025.coling-main)

Copied to clipboard

Challenge: Recent research in large language models (LLMs) has focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLM to small language models at downstream clients.
Approach: They propose a parameter-efficient federated mutual knowledge transfer framework for large and small language models that allows for token alignment and selective knowledge transfer between client-side LLMs and a server-side SLM.
Outcome: The proposed framework enhances the performance of both LLMs and SLMs with clients' unique domain insights while preserving the server's LLM and client's unique domain insight.
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have made great progress in code generation, however, they still produce errors.
Approach: They propose a RL environment that provides feedback on code editing by analyzing the performance of the revised code in unit tests.
Outcome: The proposed model outperforms baselines in enhancing open-source code LLMs’ code editing, making them comparable with closed-source LLM.
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning Large Language Models (LLMs) suffer from a performance bottleneck . Existing approaches like Offsite-Tuning (OT) secure the LLMs IP .
Approach: They propose a framework that replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM) they propose 'resource-friendly' compression and 'robust optimization' to handle data heterogeneity.
Outcome: Experiments show that FedProxy outperforms OT and centralized fine-tuning methods.
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents (2023.emnlp-main)

Copied to clipboard

Challenge: a human-like chatbot requires commonsense reasoning to comprehend and respond to information . however, identifying and aggregating key evidence within a single hop is a challenge . a knowledge distillation framework is proposed that leverages LLMs as unreliable teachers .
Approach: They propose a framework that leverages large language models as unreliable teachers to facilitate multi-hop reasoning over a dialogue context.
Outcome: The proposed framework leverages LLMs as unreliable teachers and selectively distills consistent and helpful rationales via alignment filters.
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods focus on layer-selective and data-selectory fine-tuning, but ignore the fact that different data points contribute varying degrees to distinct model layers.
Approach: They propose a method that performs selective fine-tuning at both data and layer dimensions as integral components of a unified optimization strategy.
Outcome: Experiments show that the proposed method outperforms baseline methods in terms of performance and performance.
DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to fine-tune large language models pose privacy risks . researchers have synthesized data with strong generation capabilities closed-source LLMs to alleviate this problem .
Approach: They propose to combine general LLMs with genetic algorithm to produce relevant and diverse synthetic text under differential privacy constraints.
Outcome: The proposed method significantly improves the performance of the model in downstream tasks while ensuring privacy.
CritiQ: Mining Data Quality Criteria from Human Preferences (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to train language models rely on manual design, perplexity, or careful prompt engineering.
Approach: They propose a method that automatically mines criteria from human preferences for data quality with only 30 human-annotated pairs and performs efficient data selection.
Outcome: The proposed method improves on human-annotated test sets and shows high accuracy on code, math, and logic domains.
Code-Switching for Enhancing NMT with Pre-Specified Translation (N19-1)

Copied to clipboard

Challenge: Existing methods to constrain NMT use placeholder tags for lexicon words and hard constraints during decoding.
Approach: They propose to use placeholder tags to replace lexicon words with target translations . they use a data augmentation method to make code-switched training data .
Outcome: The proposed method improves translation quality without hurting unconstrained words.
Content- and Topology-Aware Representation Learning for Scientific Multi-Literature (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches focus on learning textual information at sentence- or document-level, but ignore inter-document connections.
Approach: They propose a model that extends representation learning to the multi-document level . it integrates latent semantic and rich relatedness information from topological networks .
Outcome: The proposed model learns latent semantic information from content and rich relatedness information from topological networks.
Semformer: Transformer Language Models with Semantic Planning (2024.emnlp-main)

Copied to clipboard

Challenge: Neural language models (LLMs) employ teacher forcing to predict tokens based on preceding ground truth tokens.
Approach: They propose a method for training a Transformer language model that explicitly models the semantic planning of response.
Outcome: The proposed method exhibits near-perfect performance and mitigates shortcut learning.
Knowledge Triplets Derivation from Scientific Publications via Dual-Graph Resonance (2024.lrec-main)

Copied to clipboard

Challenge: Existing relation extraction methods aim to extract explicit triplet knowledge from documents, but they can hardly perceive unobserved factual relations.
Approach: They propose a novel Extraction-Contextualization-Derivation strategy to generate a document-specific dynamic graph from a shared static knowledge graph.
Outcome: The proposed method can generate richer explicit and implicit relations under the guidance of static and dynamic knowledge topologies.

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