Papers by Xue He

25 papers
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a novel post-training pruning method relies on the Hessian matrix to perform pruning . current pruning methods are computationally intensive and lack performance due to second-order derivative calculations.
Approach: They propose a Hessian-free weight pruning method that reduces computational burden . they use an Exponentially Weighted Moving Average technique to bypass weight sorting .
Outcome: The proposed method achieves hardware-efficient model compression by eliminating computational intensive calculations.
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.
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning (2024.lrec-main)

Copied to clipboard

Challenge: General pre-trained language models (PLMs) leverage relation triples from knowledge graphs (KGs) and integrate external data sources into language models via self-supervised learning.
Approach: They propose to learn Knowledge-Enhanced language representations with Hierarchical Reinforcement Learning (KEHRL) to detect positions for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.
Outcome: The proposed model can detect essential positions in texts for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions.
Approach: They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models.
Outcome: The proposed benchmarks show that the models perform better in open-ended conversations.
Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks .
Approach: They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario.
Outcome: The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models.
CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Copied to clipboard

Challenge: Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach: They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome: The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.
TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for incorporating external knowledge into language models do not prioritize learning embeddings for entity-related tokens.
Approach: They propose a framework for incorporating external knowledge into pre-training models that utilize entity-related tokens.
Outcome: The proposed framework reduces pre-training time by 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.
Rationales for Answers to Simple Math Word Problems Confuse Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies show that large language models have advanced mathematical problem-solving abilities in grade school math word problems.
Approach: They propose to combine fine-tuning and prompt-based methods to improve performance . they propose to use a hybrid algorithm to fine- tune LLMs on specific tasks .
Outcome: The proposed methods improve performance on the proposed reasoning process evaluation benchmarks.
SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction (2020.acl-main)

Copied to clipboard

Challenge: Aspect terms and opinion terms are key problems of fine-grained aspect-based sentiment analysis.
Approach: They propose a method to extract aspect and opinion terms as pairs from a sentence . they use shared spans to extract the terms under supervision of span boundaries .
Outcome: The proposed method outperforms state-of-the-art methods on both aspects and opinion terms extraction tasks.
Attention Consistency for LLMs Explanation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing interpretability methods face limitations such as low resolution and high computational cost.
Approach: They propose a multi-layer attention consistency score to estimate the importance of input tokens in large language models.
Outcome: The proposed heuristic achieves a favorable trade-off between interpretability quality and computational efficiency .
Don’t Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction (2026.acl-long)

Copied to clipboard

Challenge: Existing GUI agents assume deterministic environment responses, generating actions without verifying whether previous operations succeeded.
Approach: They propose a GUI agent that explicitly models action outcomes and recovery under noisy environments.
Outcome: The proposed agent reduces failure loops and improves recovery success in noisy environments while maintaining competitive standard task performance.
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)

Copied to clipboard

Challenge: FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions .
Approach: They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures .
Outcome: The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes.
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for activation sparsification do not capture the relationship between activation and model performance.
Approach: They propose a general activation sparsification approach using channel-wise thresholding and selective sparsifying to capture the relationship between activation and model performance.
Outcome: The proposed approach reduces the number of activated neurons during inference by 1.27x over eight downstream tasks while activating fewer parameters than existing methods.
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on how SAEs derive most fine-grained latent features for safety remain unexplored.
Approach: They propose a framework for interpreting SAE features in safety-critical domains . they train a suite of SAEs with human-readable explanations and systematic evaluations based on pornography, politics, violence, and terror .
Outcome: The proposed framework reduces interpretation cost by 55% and improves safety-critical features.
The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Existing work on instruction tuning has focused on task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations.
Approach: They propose a training data arrangement framework that allows for continual learning and loss reduction.
Outcome: The proposed framework promotes continual learning and loss reduction on unseen tasks.
A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization (2025.findings-acl)

Copied to clipboard

Challenge: Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache.
Approach: They propose a retrieval-based method to reduce the memory footprint of LLMs . they propose Windowed Rotary Position Embedding and query-aware vector quantization .
Outcome: The proposed method can achieve lower performance degradation with lower overhead compared to existing methods . it can reduce the memory footprint and access overhead of long context large language models .
Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios.
Approach: They propose a framework that internalizes domain knowledge through internal-external knowledge self-selection and selective supervised fine-tuning.
Outcome: The proposed framework outperforms existing methods and matches domain-pretrained LLMs with significantly lower cost.
RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in many areas but face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA).
Approach: They propose a framework to enhance models’ reasoning capability through iterative self-exploration that addresses key errors in MHQA tasks such as Evidence Aggregation and Reasoning Decomposition.
Outcome: Extensive experiments on multiple MHQA benchmarks show that the proposed framework significantly improves reasoning accuracy and task performance.
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis (2026.acl-long)

Copied to clipboard

Challenge: Aspect-based sentiment analysis (ABSA) has seen success with English texts, but real-world social media interactions often involve multiple languages.
Approach: They propose a framework for cross-lingual ABSA that incorporates code-switched bilingual sentences into the language discriminator and consistency training modules to enhance cross-linguistic alignment.
Outcome: The proposed framework achieves cross-lingual sentence-level and aspect-level alignment, aligning features of aspect terms in different contextual environments.
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach: They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome: The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Extending CoT through RL can induce undesirable thinking patterns such as overthinking . prior work has focused on inefficient reflection, which manifests in two problematic patterns: Indiscriminate Reflection and Repetitive Reflectione .
Approach: They propose a graph-based approach to optimize CoT by pruning each linear CoT into a directed acyclic graph with explicit dependency edges.
Outcome: The proposed approach reduces the average reasoning tokens by 42% while maintaining or improving accuracy.
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences.
Approach: They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives.
Outcome: The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs.
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for efficient deployment of small language models face inefficient bit-width allocation and insufficient fine-grained quantization adjustments.
Approach: They propose a weight quantization technique that facilitates efficient deployment of SLMs . they propose to combine inter-layer loss and intra-layer salience to achieve better allocation .
Outcome: Experimental results show that multi-level weight quantization achieves competitive performance compared to state-of-the-art methods.
UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies rely on shallow unsupervised data generated by token surface matching regardless of global context-aware semantics of the surrounding text tokens.
Approach: They propose an Unsupervised Pseudo Semantic Data Augmentation mechanism to enrich training data without human intervention.
Outcome: The proposed model improves on general zero-shot cross-lingual understanding tasks on different languages without human intervention.

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