Papers by Wei Xi

31 papers
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

Copied to clipboard

Challenge: Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach: They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome: The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.
Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder (2021.acl-long)

Copied to clipboard

Challenge: Existing efforts to capture event argument interactions are limited by the argument role type information of contextual entities.
Approach: They propose to capture event argument interactions as a Seq2Seq-like learning problem where a sentence with a specific event trigger is mapped to a sequence of event argument roles.
Outcome: The proposed neural architecture generates argument roles by incorporating contextual entities’ argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach: They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome: The proposed framework reduces token usage by 69.7% on AIME24.
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Copied to clipboard

Challenge: Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach: They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome: The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026.acl-long)

Copied to clipboard

Challenge: MCTS methods retain only the single highest-reward trajectory, discarding comparative signals present in the many explored paths.
Approach: They propose a framework that transforms supervision extraction into a synthesis procedure.
Outcome: The proposed framework matches or exceeds baselines on 60K CRPS-synthesized examples on out-of-domain benchmarks.
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks (N19-1)

Copied to clipboard

Challenge: Existing distance supervised relation extraction models for long-tail data are inadequate for many applications.
Approach: They propose to leverage implicit relational knowledge among class labels and learn explicit relational knowing using graph convolution networks.
Outcome: The proposed approach outperforms baselines for long-tail relations on a large-scale dataset.
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach: They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome: The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations.
Approach: They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries.
Outcome: The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision.
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach: They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome: The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
DESED: Dialogue-based Explanation for Sentence-level Event Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for sentence-level event detection depend on manual annotations or domain expertise to design sophisticated templates and rules.
Approach: They propose a dialogue-based explanation paradigm to enhance sentence semantics for event detection.
Outcome: The proposed method can be applied to two event detection datasets.
Improving Embedding-based Large-scale Retrieval via Label Enhancement (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for large-scale retrieval are trained with 0-1 hard labels that indicate whether a query is relevant to a document, ignoring rich information of the relevance degree.
Approach: They propose to introduce label enhancement for the first time to characterize query-document relevance degree by embedding label distribution into contextual embeddables.
Outcome: The proposed method significantly outperforms existing retrieval models and its counterparts equipped with two alternative methods on English and Chinese large-scale retrieval tasks.
Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to generate answer summarization for medical questions are not straightforward to apply to the medical domain.
Approach: They propose an approach that utilizes graph convolution networks and question-focused dual attention for Chinese medical answer summarization.
Outcome: The proposed model generates more coherent and informative summaries compared with baseline models.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Copied to clipboard

Challenge: Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach: They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome: The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.
Connectivity Patterns are Task Embeddings (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for predicting inter-task transferability are sparse and task-specific.
Approach: They propose a method that uses connectivity patterns of neurons as a unique identifier associated with a task.
Outcome: The proposed method outperforms baselines in predicting inter-task transferability across data regimes and transfer settings while keeping high efficiency in computation and storage.
Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach: They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome: The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Copied to clipboard

Challenge: Existing methods to generate large scale labeled data for relation extraction produce noisy relation labels when there are multiple relationships between entities.
Approach: They propose a method which assumes that a pair of entities appears in a Knowledge Graph and trains a relation classifier.
Outcome: The proposed method performs well in the current distant supervision dataset.
LegalCore: A Dataset for Event Coreference Resolution in Legal Documents (2025.findings-acl)

Copied to clipboard

Challenge: Existing research on event coreference resolution is limited to news articles . existing datasets for news articles are limited to events and coreferences .
Approach: They present a dataset for the legal domain LegalCore which has been annotated with event and event coreference information.
Outcome: The legal contract documents annotated in this dataset are several times longer than news articles, with an average length of around 25k tokens per document.
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach: They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome: Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.
ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on role-playing focuses on textual modalities, neglecting speech . et al., 2025) show that speech role-players can generate spontaneous responses with personalized traits based on the context.
Approach: They propose a framework that allows models to deliver spontaneous responses with personalized verbal traits based on their role, scene, and spoken dialogue.
Outcome: The proposed framework enhances speech role-playing by generating spontaneous responses with personalized traits based on their role, scene, and spoken dialogue.
UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Copied to clipboard

Challenge: Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach: They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome: The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.
Label Smoothing for Text Mining (2022.coling-1)

Copied to clipboard

Challenge: Existing text mining models are trained with 0-1 hard label that indicates whether an instance belongs to a class, ignoring rich information of the relevance degree.
Approach: They propose a keyword-based method to automatically generate soft labels from hard labels . they exploit relevance between labels and instances to incorporate them into models .
Outcome: The proposed method improves models under balanced and unbalanced conditions.
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts (2022.emnlp-main)

Copied to clipboard

Challenge: Recent efforts to classify unstructured texts into specific types have been limited in practical scenarios.
Approach: They propose to use Chinese text conversations and phone conversations to expand event detection to the scenarios involving informal and heterogeneous texts.
Outcome: The proposed dataset is based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries.
Approach: They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation.
Outcome: The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks.
ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry (2025.acl-industry)

Copied to clipboard

Challenge: Existing methods for Community Question Answering (CQA) focus on static knowledge, limiting their applicability to real-world scenarios.
Approach: They propose a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism.
Outcome: The proposed framework outperforms baselines on three industrial CQA datasets and achieves 25.9% improvement in vector similarity, reducing latency by 8.7%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.
Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction (D18-1)

Copied to clipboard

Challenge: Existing neural networks focus on instance representation, and subsampling fails to retain precise spatial relationships between higher-level parts.
Approach: They propose a neural approach based on capsule networks with attention mechanisms to extract relational information from a capsule.
Outcome: The proposed method improves the precision of the predicted relations with different benchmarks.
Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)

Copied to clipboard

Challenge: Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects.
Approach: They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.
Outcome: The proposed framework outperforms existing methods that generate SQL queries directly.
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Copied to clipboard

Challenge: e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach: They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome: The proposed model outperforms baseline models and provides better recall and triage for specialized agents.
Distill Visual Chart Reasoning Ability from LLMs to MLLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: a new method for generating chart annotations is proposed to improve visual reasoning in multimodal large language models.
Approach: They propose a code-as-intermediary translation method for distilling visual reasoning abilities from LLMs to MLLMs.
Outcome: The proposed method is cost-effective, efficient and scalable.
SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for pretraining data mixing for large language models neglect significant inter-domain overlaps and commonalities, failing to control the global diversity of the constructed training dataset.
Approach: They propose a sample-wise data mixture approach that performs global cross-domain sampling by systematically evaluating the quality and diversity of each sample.
Outcome: The proposed method exceeds existing domain-based methods in multiple downstream tasks and perplexity assessments.
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for large-scale query-document retrieval are expensive and require sparse handcrafted features.
Approach: They propose a quadrupletBERT model for effective and efficient retrieval using pre-trained language models like BERT.
Outcome: The proposed model improves retrieval phase and leverages distances between simple negative and hard negative instances to obtain better embeddings.

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