Papers by Xixin Wu

12 papers
Autoregressive Speech Synthesis without Vector Quantization (2025.acl-long)

Copied to clipboard

Challenge: MELLE is a novel language modeling approach for text-to-speech synthesis that generates continuous tokens from text . authors demonstrate that it reduces the need for vector quantization and improves model robustness .
Approach: They propose to autoregressively generate continuous mel-spectrogram frames directly from text condition, bypassing vector quantization.
Outcome: The proposed model achieves superior performance across multiple metrics and is more streamlined.
Rethinking Machine Ethics – Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? (2024.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to making moral judgments are mostly bottom-up and lack explainability.
Approach: They propose a top-down framework to steer Large Language Models to perform moral reasoning with well-established moral theories.
Outcome: The proposed framework can integrate various moral theories on moral datasets.
Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach: They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome: The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.
Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to incorporate retriever’s preference during the training of query rewriting models rely on extensive annotations such as in-domain rewrites and/or relevant passage labels, limiting their generalization and adaptation capabilities.
Approach: They propose a framework for training query rewriting models with limited rewrite annotations from seed datasets and completely no passage label.
Outcome: The proposed approach decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers.
Search Augmented Instruction Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information.
Approach: They propose a search-augmented instruction learning model which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines.
Outcome: The proposed model outperforms plain LLMs on zero-shot language tasks and can generate both natural and programming languages following natural language guidance and requests.
Coupling Global and Local Context for Unsupervised Aspect Extraction (D19-1)

Copied to clipboard

Challenge: Existing studies on aspect extraction focus on sequence tagging models trained on human-annotated data.
Approach: They propose a novel neural model capable of coupling global and local representations to discover aspect words by combining global and locale contexts.
Outcome: The proposed model outperforms state-of-the-art models on laptop and restaurant reviews on two benchmarks.
Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve context faithfulness in large language models are either inadequate or overlook the potential for self-improvement.
Approach: They propose a framework that enhances context faithfulness through fine-grained sentence-level optimization.
Outcome: Experiments on ASQA and ConFiQA datasets show that GenDiE surpasses baselines in faithfulness and correctness and exhibits robust performance for domain adaptation.
RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation frameworks rely on direct prompting of resource-intensive models with complex multi-stage prompts, introducing significant computational cost and underutilizing models’ reasoning capabilities.
Approach: They propose a framework that trains evaluators with reinforcement learning to generate comprehensive and sound assessments with detailed explanation in one-pass.
Outcome: The proposed framework outperforms baseline evaluation frameworks that rely on LLMs with 10-100 more parameters and achieves the strongest correlation with human judgments.
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for surfacing symbolic reasoning capabilities are limited to narrow tasks . arithmetic computations are unnatural to perform in pure language space, and hence present difficulties for LLMs.
Approach: They propose a natural language embedded program framework for solving symbolic reasoning tasks.
Outcome: The proposed framework improves on strong baselines across math and symbolic reasoning, text classification, question answering, and instruction following tasks.
Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases (2022.coling-1)

Copied to clipboard

Challenge: Existing generation-based KBQA methods that translate natural language questions to executable logical forms are proving promising but noise introduced can lead to incorrect results.
Approach: They propose a Generation-based KBQA method that uses auxiliary information to enhance logical form generation by combining unseen KB items with novel combinations.
Outcome: The proposed method achieves state-of-the-art results on ComplexWebQuestions and WebQuestIONSSP datasets.
Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains (2025.acl-long)

Copied to clipboard

Challenge: Existing research on the utilization of Knowledge Graphs (KGs) for large language models (LLMs) relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs’ step-wise reasoning capabilities and KGs’ structural nature.
Approach: They propose a graph-aware constrained decoding framework that facilitates a deep synergy between LLMs and KGs by constraint derived from the topology of the KG.
Outcome: The proposed framework can provide faithful and sound reasoning for KGQA.
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for speech generation rely on subjective, expensive judgments . Existing models only cover a narrow set of scenarios and only provide limited coverage .
Approach: They propose a unified speech reward model that can support multi-dimensional, interpretable reward signals with reliable reasoning.
Outcome: The proposed model can support multi-dimensional, interpretable reward signals with reliable 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