Papers by Xingwei He

17 papers
Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation (2025.findings-acl)

Copied to clipboard

Challenge: High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity.
Approach: They propose a framework that compresses instructions into a compact tag space and enhances complexity through RL-guided tag expansion.
Outcome: The proposed framework outperforms existing methods in the evaluation of instruction complexity augmentation and semantic compression of text into a compact tag space.
Noisy Pair Corrector for Dense Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing dense retrieval models assume that query-document pairs are exactly matched, resulting in mismatched-pair noise.
Approach: They propose a novel approach to train an effective model with mismatched-pair noise.
Outcome: The proposed model performs well on natural question and triviaQA, code-search benchmarks and SO-DS.
Parallel Refinements for Lexically Constrained Text Generation with BART (2021.emnlp-main)

Copied to clipboard

Challenge: Existing work injects lexical constraints into the output, which generates generic or ungrammatical sentences and has high computational complexity.
Approach: They propose a model that incorporates pre-specified keywords into the output to control the generated text.
Outcome: The proposed model decomposes the generated text into two sub-tasks and improves the sentence quality.
Extracting Event Temporal Relations via Hyperbolic Geometry (2021.emnlp-main)

Copied to clipboard

Challenge: Recent neural approaches to event temporal relation extraction map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs.
Approach: They propose to embed events into hyperbolic spaces to model hierarchical structures . they propose to use hyperbolical embeddings to directly infer event relations .
Outcome: The proposed architecture is based on two approaches to encode events and their temporal relations in hyperbolic spaces.
Controllable Dictionary Example Generation: Generating Example Sentences for Specific Targeted Audiences (2022.acl-long)

Copied to clipboard

Challenge: Traditionally, example sentences are created by linguistics experts, which are labor-intensive and knowledge-intensive . linguistic experts create dictionary examples for polysemous words, which can be difficult for polygraphs . authors propose a model that generates reasonable examples for targeted words .
Approach: They propose a controllable dictionary example sentence generation model that generates appropriate examples for targeted words . model allows users to provide explicit control over attributes related to readability .
Outcome: The proposed model generates reasonable examples for targeted words even for polysemous words while providing explicit control over readability attributes.
PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for Factual Error Correction (FEC) use mask-then-correct paradigms . however, the lack of datasets containing false claims has impeded progress .
Approach: They propose a method that enhances few-shot FEC with a pivot task approach using large language models.
Outcome: The proposed method outperforms its few-shot counterpart by 7.9 points in SARI . it improves widely-adopted SARI metrics by 11.3 compared to the best-performing methods .
Event Temporal Relation Extraction with Bayesian Translational Model (2023.eacl-main)

Copied to clipboard

Challenge: Existing methods to extract temporal relations between events lack a principled method to incorporate external knowledge.
Approach: They propose a Bayesian-based method that models the temporal relation representations as latent variables and infers their values via Bayessian inference and translational functions.
Outcome: The proposed method outperforms existing methods for event temporal relation extraction on three widely used datasets.
Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing QA frameworks that use event-centric reasoning are lacking.
Approach: They propose a novel QA model with contrastive learning and invertible event transformation . they use an invertable transformation matrix to project event vectors into a common event embedding space .
Outcome: The proposed model achieves 8.4% gain in token-level F1 score and 3.0% gain in Exact Match score on the ESTER dataset.
Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval (2024.lrec-main)

Copied to clipboard

Challenge: Existing mPLMs neglect the importance of knowledge in cross-lingual dense retrieval.
Approach: They propose a novel mPLM that leverages knowledge to learn language-agnostic semantic representations from a multilingual knowledge base and an annotation of Wiki.
Outcome: The proposed model achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.
Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing work on commonsense generation requires models to have relational reasoning and compositional generalization capabilities.
Approach: They propose a metric distillation rule to distill knowledge from a standard metric to a ranker and transfer it to re-ranking a retriever.
Outcome: The proposed method surpasses the previous SOTA.
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach: They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome: The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion (2023.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that dense retrieval models are better at obtaining query-informed representations.
Approach: They propose a dual-encoder approach that computes latent representations of query and document independently, but inference replaces the real query with a generated one.
Outcome: The proposed approach outperforms previous dense retrieval models on in-domain and out-of-domain datasets.
Cascading Large Language Models for Salient Event Graph Generation (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies on event graph generation rely on distant supervision for event graphs .
Approach: They propose a CAscading Large Language Model framework for SAlient Event graph generation which leverages the capabilities of LLMs and eliminates the need for costly human annotations.
Outcome: The proposed method outperforms baseline models on a human-annotated test set.
Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for constructing event temporal graphs have been suboptimal . authors propose a set-aligning framework for the effective utilisation of Large Language Models .
Approach: They propose a set-aligning framework for the effective utilisation of Large Language Models to alleviate text generation loss penalties.
Outcome: The proposed framework surpasses existing baselines for event temporal graph generation.
Efficient Test-Time Scaling via Temporal Reasoning Aggregation (2026.findings-acl)

Copied to clipboard

Challenge: Existing dynamic early-exit methods rely on single-step confidence signals . existing approaches are unreliable for detecting reasoning convergence in multi-step settings .
Approach: They propose a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals.
Outcome: Experiments show that TRACE reduces reasoning token usage by 25% on average while maintaining accuracy within 1–2% of full-length reasoning.
GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing models for long contexts struggle to handle long inputs due to limited context window and memory usage.
Approach: They propose a graph-based agent system that analyzes long texts into a graphical graph . GraphReader consistently outperforms GPT-4-128k across context lengths from 16k to 256k .
Outcome: The proposed model outperforms existing models on four challenging benchmarks.
MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to offline reinforcement learning (RL) focus on learning value functions or policy gradients, but they view it as a sequence modeling task.
Approach: They propose a method that integrates multimodal and pre-trained language models to transform offline reinforcement learning into a supervised learning task by integrating state information derived from images and action-related data obtained from text.
Outcome: The proposed approach outperforms baselines on Atari and OpenAI Gym environments while promoting long-term strategic thinking.

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