Papers by Xiangyang Liu

15 papers
Flames: Benchmarking Value Alignment of LLMs in Chinese (2024.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) do not accurately uncover safety vulnerabilities in LLMs.
Approach: They propose a value alignment benchmark called Flames that encompasses both harmlessness principles and a unique morality dimension that integrates specific Chinese values such as harmony.
Outcome: The proposed model performs poorly on Flames, particularly in safety and fairness dimensions.
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on detecting LLM’s confidence via statistical uncertainty.
Approach: They propose to use a representation perspective to solve adaptive RAG by enabling dynamic retrieval during generation and enabling retrieval only when the query exceeds LLM's internal knowledge.
Outcome: The proposed framework is superior to existing adaptive RAG methods on a diverse set of tasks.
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)

Copied to clipboard

Challenge: Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability.
Approach: They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks.
Outcome: The proposed model outperforms or performs on par with SOTA compressed and early exiting models.
Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to rerank and align documents based on reasoning capabilities of large language models (LLMs) . prior work shows that LLMs have exceptional reasoning and text generation capabilities .
Approach: They propose a rationale extraction method that leverages reasoning capabilities of large language models to extract the rationales necessary for answering a query.
Outcome: The proposed method is compared with baseline methods on two tasks across three datasets.
Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator (2022.coling-1)

Copied to clipboard

Challenge: Existing studies on controlled text generation focus on single-attribute control, but in practical applications, they lack controllability.
Approach: They propose a framework for multi-attribute controlled text generation that can effectively generate texts with more attributes.
Outcome: The proposed framework achieves remarkable controllability while keeping the text fluent and diverse.
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (P18-1)

Copied to clipboard

Challenge: Existing models for matching dialogue responses rely on semantic and functional dependencies . a recent study only uses the last utterance in context for matching a reply .
Approach: They propose a model that matches a response with its multi-turn context using attention.
Outcome: The proposed model outperforms the state-of-the-art models on two large-scale multi-turn response selection tasks.
Contrastive Learning enhanced Author-Style Headline Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Current work only uses the article itself in the headline generation, but have not taken the writing style of headlines into account.
Approach: They propose a model which takes historical headlines into account to integrate the stylistic features of the author into the model and integrate them into the decoder.
Outcome: The proposed model can integrate the stylistic features of the author into the model and generate a headline that is appropriate for the article and consistent with the author’s style.
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer.
Approach: They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer.
Outcome: The proposed approach improves on learning to exit and predicting instance difficulty.
Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning (2024.lrec-main)

Copied to clipboard

Challenge: Existing image captioning models require large trainable parameters to bridge visual and textual representations.
Approach: They propose a lightweight image captioning network in combination with continuous diffusion that injects prefix image embeddings into denoising process of diffusion model.
Outcome: The proposed method generates diverse captions with relatively less parameters while maintaining fluency and relevance compared with other models.
MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for document question answering do not consider content structures, resulting chunks exclude vital information or include irrelevant content.
Approach: They propose a method that segments document into content chunks and represents each content chunk in raw-text, keywords, and summary views.
Outcome: The proposed method significantly improves recall of long document question answering datasets compared to state-of-the-art chunking schemes.
D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension (D19-58)

Copied to clipboard

Challenge: MRC requires machines to understand text and answer questions about the text.
Approach: They propose a simple system Baidu submitted for MRQA 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.
Outcome: The proposed system is ranked at top 1 of all participants in terms of averaged F1 score.
Star-Transformer (N19-1)

Copied to clipboard

Challenge: Existing models with fully-connected attention connections are heavy and require large training data.
Approach: They propose a lightweight alternative to the Transformer by sparsifying the fully-connected structure with a star-shaped topology.
Outcome: The proposed model achieves significant performance improvements on 22 datasets on four tasks.
Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts (2022.findings-emnlp)

Copied to clipboard

Challenge: Prompt tuning is parameter-efficient but lags behind other state-of-the-art methods.
Approach: They propose a parameter-efficient tuning method that only optimizes a soft prompt to adapt PTMs to downstream tasks.
Outcome: The proposed method is parameter-efficient but lags behind other state-of-the-art methods.
Plug-and-Play Document Modules for Pre-trained Models (2023.acl-long)

Copied to clipboard

Challenge: Large-scale pre-trained models have been widely adopted for document-oriented NLP tasks, such as question answering.
Approach: They propose to decouple document encoding from downstream tasks by introducing a document plugin into the backbone of a PTM.
Outcome: The proposed model can encode documents once and for all across different scenarios.
Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies show that large language models can perform complex reasoning tasks without labeled data and unlabeled data.
Approach: They propose a framework for solving reasoning tasks that store answers in a streaming experience pool and orchestrate helpful questions from the pool to assist itself in answering new questions.
Outcome: The proposed framework can self-improve as it answers reasoning questions . it stores all answered reasoning questions and their reasoning steps in a streaming experience pool .

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