Papers by Xiang Deng

28 papers
ReasonBERT: Pre-trained to Reason with Distant Supervision (2021.emnlp-main)

Copied to clipboard

Challenge: Existing pre-training methods only harvest learning signals from local contexts of naturally occurring texts . ReasonBert provides a method for reasoning over long-range relations and multiple, possibly hybrid contexts.
Approach: They propose a method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts.
Outcome: The proposed method significantly improves sample efficiency over strong baselines.
Synergizing Stylometrics with Semantics: Dual-Path Framework for LLM Detection and Attribution (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for identifying MGTs rely on statistical likelihood or deep embeddings.
Approach: They propose a framework that extracts model-specific stylistic fingerprints across lexical, syntactic, and structural dimensions.
Outcome: The proposed framework achieves a Macro-F1 score of 95.6% on the Wikipedia dataset.
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches for Named Entity Recognition (NER) use extensive labeled data for model training, which struggles in low-resource scenarios.
Approach: They propose a lightweight tuning paradigm for low-resource NER via pluggable prompting . they construct a learnable verbalizer of entity categories without any label-specific classifiers .
Outcome: The proposed model outperforms baselines and class transfer models in low-resource scenarios.
Iteratively Prompt Pre-trained Language Models for Chain of Thought (2022.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) internalize a great amount of knowledge, but have been shown incapable of recalling this knowledge to solve complex & multi-step reasoning tasks.
Approach: They propose an iterative prompting framework which progressively elicits relevant knowledge from PLMs for multi-step inference.
Outcome: The proposed prompting framework outperforms existing prompting methods on three datasets involving multi-step reasoning.
Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches for named entity recognition and relation extraction suffer from error sensitivity when irrelevant object images are incorporated in texts.
Approach: They propose a hierarchical visual prefix fusion NeTwork for visual-enhanced entity and relation extraction using pluggable visual prefixed visual features.
Outcome: The proposed method achieves state-of-the-art on three benchmark datasets.
I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)

Copied to clipboard

Challenge: Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process .
Approach: They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.
Outcome: The proposed paradigm outperforms existing methods in compositional editing tasks.
Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)

Copied to clipboard

Challenge: Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach: They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome: The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexity of constructing tasks and evaluators.
Approach: They propose a cross-environment agent benchmark framework that integrates graph-based evaluation and task generation methods.
Outcome: The proposed framework supports multiple devices and can be easily extended to any environment with a Python interface.
Hello Again! LLM-powered Personalized Agent for Long-term Dialogue (2025.naacl-long)

Copied to clipboard

Challenge: Existing dialogue systems focus on brief single-session interactions, neglecting real-world needs for long-term companionship and personalized interactions.
Approach: They propose a model-agnostic framework for long-term dialogue agents . they use event summary and persona management to enable reasoning .
Outcome: The proposed framework incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation.
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters (2023.acl-long)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs).
Approach: They propose to use Chain-of-Thought (CoT) prompting to encourage the LLM to generate intermediate rationales for solving a problem by providing a series of reasoning steps in the demonstrations.
Outcome: The proposed model can generate coherent lines of reasoning even with invalid demonstrations while still generating coherent lines during inference.
Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing studies on English-centric translation tasks have focused on multimodal large language models, but the exploration of many-to-many translation is limited by the scarcity of parallel data.
Approach: They propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.
Outcome: The proposed strategy achieves state-of-the-art average performance in 1514 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild (2024.emnlp-demo)

Copied to clipboard

Challenge: Currently, the volume and complexity of chat logs makes it difficult to analyze individual conversations.
Approach: They propose a tool that enables fast, versatile, and large-scale conversation analysis by combining search and visualization capabilities with a list of criteria.
Outcome: The proposed tool can be extended to handle millions of chat logs and other datasets.
Reasoning with Language Model Prompting: A Survey (2023.acl-long)

Copied to clipboard

Challenge: Reasoning is an essential ability for complex problem-solving and can provide back-end support for various real-world applications.
Approach: They present cutting-edge research on reasoning with language model prompting and provide systematic resources to help beginners.
Outcome: The proposed approaches have not been systematically reviewed and analyzed.
Don’t Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments (2023.acl-long)

Copied to clipboard

Challenge: Existing language models lack grounding to real-world environments . a missing piece is the connection between LMs and the environment .
Approach: They propose a generic framework for grounded language understanding that capitalizes on discriminative ability of LMs instead of their generative ability.
Outcome: The proposed framework capitalizes on discriminative ability of LMs instead of their generative ability.
Structure-Grounded Pretraining for Text-to-SQL (2021.naacl-main)

Copied to clipboard

Challenge: STRUG is a weakly supervised structure-based pretraining framework for text-to-SQL . it can be used to learn to capture text-table alignment in a given database schema .
Approach: They propose a weakly supervised structure-grounded pretraining framework for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text-tab corpus.
Outcome: The proposed framework outperforms BERTLARGE and BERTLAGE on all text-to-SQL alignment settings.
Assessing Dialogue Systems with Distribution Distances (2021.findings-acl)

Copied to clipboard

Challenge: Existing evaluation metrics focus on turnlevel quality, which is not well suited for open-end dialogue tasks.
Approach: They propose to measure the performance of a dialogue system by computing the distributionwise distance between its generated conversations and real-world conversations.
Outcome: The proposed metrics correlate better with human judgments than existing metrics on dialogue systems.
Exploring Chain of Thought Style Prompting for Text-to-SQL (2023.emnlp-main)

Copied to clipboard

Challenge: In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks.
Approach: They propose a new chain of thought prompting method that enhances LLMs’ reasoning ability through chain of thinking prompting, including the original chain-of-thought prompting and least-to-most prompting.
Outcome: The proposed method brings 5.2 and 6.5 point absolute gains on the Spider development set and the Spider Realistic set, respectively, compared to the standard prompting method without reasoning steps; 2.4 and 1.5 point absolute gain, versus the least-to-most prompting.
Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to remove undesirable data from Large Language Models suffer from cumulative catastrophic utility loss under continuous unlearning requests.
Approach: They propose a method that leverages the rotational salience weight of RCU to quantify and control the unlearning degree in the continuous unlearning process.
Outcome: The proposed method achieves SOTA performance without a retained dataset.
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating geometric reasoning data through Chain-of-Thought (CoT) frameworks face three fundamental limitations: 1) lack of high-quality annotations and domain-specific expertise to ensure theorem-grounded diagrams. 2) lack of a coherent model; 3) lack of coherent model.
Approach: They propose a two-stage Theorem-Validated Reverse Chain-of-Thought Reasoning Synthesis framework that synthesizes theorematic diagrams with structured descriptions and properties.
Outcome: The proposed framework expands theorem-type coverage, corrects misunderstandings, and enhances geometric reasoning.
Knowledge Mechanisms in Large Language Models: A Survey and Perspective (2024.findings-emnlp)

Copied to clipboard

Challenge: Using large language models, we can understand knowledge mechanisms in LLMs for learning, storage, utilization, and evolution.
Approach: They propose to analyze knowledge mechanisms in Large Language Models (LLMs) they examine utilization, evolution, and the potential dark knowledge (hypothesis) they hope to help understand knowledge in LLMs and provide insights for future research .
Outcome: The proposed model can be used to analyze the evolution of parametric knowledge in LLMs.
RWKV-CLIP: A Robust Vision-Language Representation Learner (2024.emnlp-main)

Copied to clipboard

Challenge: Using large image-text datasets, large-scale image-data sets have been used for visionlanguage pre-training.
Approach: They propose a framework that leverages Large Language Models to combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.
Outcome: The proposed framework can combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.
M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach: They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome: The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.
GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for complex table question answering are often implicit, feeding the entire table into prompts.
Approach: They propose a GraphOTTER that explicitly establishes the reasoning process to pinpoint the correct answers.
Outcome: The proposed method is able to identify the correct answers on two benchmark datasets and two LLM backbones.
SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences.
Approach: They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context.
Outcome: The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs.
Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction (D19-1)

Copied to clipboard

Challenge: Existing methods to construct noisy labeled data for relation extraction (RE) are expensive and lacks the labeling capability.
Approach: They propose a 2-hop DS strategy to enhance distantly supervised relation extraction (RE) by combining sentences that mention entities that are linked to each other.
Outcome: The proposed method outperforms baselines on a benchmark dataset by a substantial margin.
Can Multiple-choice Questions Really Be Useful in Detecting the Abilities of LLMs? (2024.lrec-main)

Copied to clipboard

Challenge: Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) however, there are concerns about whether MCQ can truly measure LLM’s capabilities.
Approach: They propose to use multiple choice questions to evaluate large language models (LLMs) to assess their capabilities.
Outcome: The proposed methods show that MCQs are less reliable than LFGQs in terms of expected calibration error.
PanoramaRAG: Enabling Consistent Global Topic Awareness in Graph-Based RAG (2026.findings-acl)

Copied to clipboard

Challenge: Existing graph-based methods for enhancing Large Language Models (LLMs) with external knowledge are focusing on local relationships, resulting in suboptimal performance for tasks that require global context.
Approach: They propose a "panorama"-guided paradigm that integrates a light yet comprehensive "panoramic" of the corpus to guide all stages of the retrieval process.
Outcome: The proposed paradigm performs well across five datasets and a variety of tasks.

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