Papers by Sheng Zhao

22 papers
Fine-tuning Language Models for Joint Rewriting and Completion of Code with Potential Bugs (2024.findings-acl)

Copied to clipboard

Challenge: Previous work has demonstrated shortcomings of large language models of code (CodeLLMs) in completing drafty partial code with potential bugs.
Approach: They propose to use large language models of code to fine-tune their models to rewrite and complete drafty partial code into functional full programs.
Outcome: The proposed approach achieves superior pass rates over baselines and preserves the integrity of the original partial implementations.
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.
Modular and Parameter-Efficient Multimodal Fusion with Prompting (2022.findings-acl)

Copied to clipboard

Challenge: Recent research has made impressive progress in large-scale multimodal pre-training.
Approach: They propose to use prompt vectors to align multimodal modalities by pretraining text inputs with prompts or embedding vectors.
Outcome: The proposed method achieves comparable performance to several other multimodal fusion methods in low-resource settings.
Edge: Enriching Knowledge Graph Embeddings with External Text (2021.naacl-main)

Copied to clipboard

Challenge: Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.
Approach: They propose a knowledge graph enrichment framework called Edge to enhance knowledge graphs based on "hard" co-occurrence of words in knowledge graph entities and external text.
Outcome: The proposed framework achieves "soft" augmentation by combining external text with knowledge graph entities.
Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Challenge: Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach: They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome: The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.
A Unified Framework for Synaesthesia Analysis (2023.findings-emnlp)

Copied to clipboard

Challenge: Synaesthesia is a cognitive phenomenon structuring human thought and action, which makes understanding it challenging.
Approach: They propose a framework for annotating synaesthetic elements and exploring their relationship . they propose to include sensory modalities, cues and stimuli in the framework .
Outcome: The proposed framework yields state-of-the-art results, demonstrating its effectiveness.
Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on optimizing external components of CoT, but lack internal explanations for the quality of the model's outputs.
Approach: They propose an efficient method to identify reasoning-critical neurons by analyzing their activation patterns under reasoning chains of varying quality.
Outcome: The proposed method shows that neurons in the feed-forward layers are critical in the generation of high-quality reasoning chains.
CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve the reasoning performance of LLMs suffer from two major shortcomings: too lengthy input contexts and overconfidence dilemma.
Approach: They propose a method to debating among LLM agents using a sparse debator graph . they use a module called McKinsey-based Debate Matter to optimize the debators .
Outcome: The proposed method has been well demonstrated across eight datasets from four task types.
Scene Restoring for Narrative Machine Reading Comprehension (2020.emnlp-main)

Copied to clipboard

Challenge: Narrative passages describe a chain of events, which helps the machine understand the passage comprehensively.
Approach: They propose a method to let machine read narrative passages with their prior knowledge . they build a scene graph using Atomic as external knowledge and encode it with GDIN .
Outcome: The proposed method achieves state-of-the-art on a Story Cloze Test and CosmosQA datasets.
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompting methods struggle with complex tasks and reasoning stability, limiting their practical deployment.
Approach: They propose a framework that adaptively balances reasoning accuracy and computational efficiency by employing a lightweight Derailer mechanism to assess reasoning stability and selectively triggers an advanced Rerailer verification process only when necessary.
Outcome: The proposed framework achieves significant accuracy improvements (8-11%) while maintaining 2-3 times better efficiency than existing verification methods.
A Study of Non-autoregressive Model for Sequence Generation (2020.acl-main)

Copied to clipboard

Challenge: Non-autoregressive (NAR) models generate all tokens in parallel, resulting in faster generation speed compared to autoregressive models.
Approach: They propose to use knowledge distillation and source-target alignment to bridge the gap between NAR and autoregressive models in various tasks.
Outcome: The proposed techniques can speed up NAR models in some tasks but not all . the proposed techniques reduce target token dependency while allowing for faster inference .
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Copied to clipboard

Challenge: Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach: They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome: The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for memory management struggle to capture fine-grained semantic relations between queries and documents.
Approach: They propose a framework for reasoning and agentic search that grows fine-grained memory fragments from seed tokens from queries, then retraces and deep refines the memory via a contribution function.
Outcome: Experiments on eight benchmark datasets show that MemSearch-o1 significantly mitigates memory dilution and more effectively activates reasoning potential of diverse LLMs.
On Measures of Biases and Harms in NLP (2022.findings-aacl)

Copied to clipboard

Challenge: Recent studies show that natural language processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Approach: They propose a framework for harms and questions to help practitioners understand biases . they propose measurable measures to detect and mitigate biased groups .
Outcome: The proposed framework provides a framework for harms and questions for practitioners to answer to guide the development of bias measures.
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation (2024.emnlp-main)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have seen remarkable progress in providing general instruction-following ability, but struggle with critical problems when required to provide a detailed and accurate response to a visual instruction.
Approach: They propose to enhance the mapping process by using retrieval-augmented tag tokens, which contain rich object-aware information such as object names and attributes.
Outcome: The proposed model outperforms baselines that share the same language model and training data on 12 benchmarks and shows zero-shot capability when provided with specific datastores.
QSpec: Speculative Decoding with Complementary Quantization Schemes (2025.emnlp-main)

Copied to clipboard

Challenge: Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models.
Approach: They propose a quantization paradigm that decouples efficiency from quality by integrating two complementary schemes via speculative decoding.
Outcome: The proposed approach achieves 1.64x speedup without quality degradation and outperforms state-of-the-art speculative decoding methods by 1.55x in batched settings.
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks.
Approach: They propose a transformer variant with mixed attention spans that leverages the attention mechanism to capture long- and short-range dependencies in the sequence.
Outcome: The proposed model can achieve competitive performance to models with full attention while reducing computational cost (75%)
Sequence-level Large Language Model Training with Contrastive Preference Optimization (2025.findings-naacl)

Copied to clipboard

Challenge: a new method to improve the performance of large language models requires a small computational cost.
Approach: They propose a CPO procedure that can inject sequence-level information into the model at any training stage without expensive human labeled data.
Outcome: The proposed objective surpasses the next token prediction in terms of win rate in instruction-following and text generation tasks.
CoTD-PO: Chain-of-Thought Distillation with Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for chain-of-thought distillation suffer from a distribution mismatch between teacher-generated training trajectories and the student model's own generative distribution.
Approach: They propose a framework that shifts the training paradigm from passive imitation to active trajectory exploration by allowing students to sample their own answer paths.
Outcome: The proposed method outperforms standard CoT distillation baselines while mitigating mode collapse and preserving semantic diversity.
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach: They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome: The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)

Copied to clipboard

Challenge: Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL).
Approach: They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Outcome: The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications.
Approach: They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
Outcome: The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.

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