Publications (85)
Distinguishability Calibration to In-Context Learning
Hongjing Li, Hanqi Yan, Yanran Li +3
Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource set…
TDAM: a Topic-Dependent Attention Model for Sentiment Analysis
Gabriele Pergola, Lin Gui, Yulan He
We propose a topic-dependent attention model for sentiment classification and topic extraction. Our model assumes that a global topic embedding is shared across documents and emplo…
Concept Algebra for (Score-Based) Text-Controlled Generative Models
Zihao Wang, Lin Gui, Jeffrey Negrea +1
This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models. A key property of such models is that they can compos…
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives
Runcong Zhao, Qinglin Zhu, Hainiu Xu +4
Existing datasets for narrative understanding often fail to represent the complexity and uncertainty of relationships in real-life social scenarios. To address this gap, we introdu…
Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
Yanzheng Xiang, Lan Wei, Yizhen Yao +8
Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decod…
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
Zhanghao Hu, Qinglin Zhu, Runcong Zhao +4
Standard Retrieval Augmented Generation (RAG) is poorly matched to agent memory. Unlike large heterogeneous corpora, agent memory forms a bounded and coherent interaction stream in…
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
Junru Lu, Jiazheng Li, Guodong Shen +5
Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-p…
Integrated Communication and Positioning Design in RIS-empowered OFDM System: a Correlation Dispersion Scheme
Xichao Sang, Lin Gui, Kai Ying +2
In this paper, we propose a novel integrated communication and positioning design for orthogonal frequency division multiplexing system aided by a reconfigurable intelligent surfac…
Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
Xinyu Wang, Lin Gui, Yulan He
Document-level multi-event extraction aims to extract the structural information from a given document automatically. Most recent approaches usually involve two steps: (1) modeling…
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
Lin Gui, Cristina Gârbacea, Victor Veitch
This paper concerns the problem of aligning samples from large language models to human preferences using best-of- sampling, where we draw samples, rank them, and return the…
Validity and Power of Heavy-Tailed Combination Tests under Asymptotic Dependence
Lin Gui, Tiantian Mao, Jingshu Wang +1
Heavy-tailed combination tests, such as the Cauchy combination test and harmonic mean p-value method, are widely used for testing global null hypotheses by aggregating dependent p-…
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
Xinyu Wang, Hainiu Xu, Lin Gui +1
Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interp…
GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery
Italo Luis da Silva, Hanqi Yan, Lin Gui +1
Large Language Models (LLMs) show strong reasoning and text generation capabilities, prompting their use in scientific literature analysis, including novelty assessment. While eval…
Sparse Activation Editing for Reliable Instruction Following in Narratives
Runcong Zhao, Chengyu Cao, Qinglin Zhu +5
Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose…
Pull Requests as a Training Signal for Repo-Level Code Editing
Qinglin Zhu, Tianyu Chen, Shuai Lu +8
Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-ben…
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems
Italo Luis da Silva, Hanqi Yan, Lin Gui +1
The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly refle…
Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering
Zhanghao Hu, Hanqi Yan, Qinglin Zhu +3
Large language models have recently pushed open domain question answering (ODQA) to new frontiers. However, prevailing retriever-reader pipelines often depend on multiple rounds of…
Position-Based Interference Elimination for High Mobility OFDM Channel Estimation in Multi-cell Systems
Xiang Ren, Wen Chen, Bo Gong +2
Orthogonal frequency-division multiplexing (OFD-M) and multi-cell architecture are widely adopted in current high speed train (HST) systems for providing high data rate wireless co…
A Survey of Automatic Hallucination Evaluation on Natural Language Generation
Siya Qi, Lin Gui, Yulan He +1
The rapid advancement of Large Language Models (LLMs) has brought a pressing challenge: how to reliably assess hallucinations to guarantee model trustworthiness. Although Automatic…
Panoptic Studio: A Massively Multiview System for Social Interaction Capture
Hanbyul Joo, Tomas Simon, Xulong Li +10
We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is fun…
SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers
Yanzheng Xiang, Hanqi Yan, Shuyin Ouyang +2
This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm compreh…
A new neighborhood structure for job shop scheduling problems
Jin Xie, Xinyu Li, Liang Gao +1
Job shop scheduling problem (JSP) is a widely studied NP-complete combinatorial optimization problem. Neighborhood structures play a critical role in solving JSP. At present, there…
Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
Junkai Zhang, Zihao Wang, Lin Gui +7
Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality output…
Multi-modal Stance Detection: New Datasets and Model
Bin Liang, Ang Li, Jingqian Zhao +5
Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets. Previous work on stance detection largely…
Heuristics for Vehicle Routing Problem: A Survey and Recent Advances
Fei Liu, Chengyu Lu, Lin Gui +3
Vehicle routing is a well-known optimization research topic with significant practical importance. Among different approaches to solving vehicle routing, heuristics can produce a s…
Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction
Hanqi Yan, Lin Gui, Gabriele Pergola +1
The Emotion Cause Extraction (ECE)} task aims to identify clauses which contain emotion-evoking information for a particular emotion expressed in text. We observe that a widely-use…
Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens
Yizhen Yao, Qinglin Zhu, Runcong Zhao +4
The paper introduces Anchor Supervised Revocable Decoding (ASRD), a training‑free method that uses temporally consistent anchor tokens to guide and verify generation in diffusion l…
PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
Qinglin Zhu, Runcong Zhao, Bin Liang +3
We introduce WellPlay, a reasoning dataset for multi-agent conversational inference in Murder Mystery Games (MMGs). WellPlay comprises 1,482 inferential questions across 12 games,…
Supervised Contrastive Learning for Multimodal Unreliable News Detection in COVID-19 Pandemic
Wenjia Zhang, Lin Gui, Yulan He
As the digital news industry becomes the main channel of information dissemination, the adverse impact of fake news is explosively magnified. The credibility of a news report shoul…
Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
Zhanghao Hu, Qinglin Zhu, Siya Qi +3
Large Language Models (LLMs) have shown improved generation performance through retrieval-augmented generation (RAG) following the retriever-reader paradigm, which supplements mode…
Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
Hanqi Yan, Qinglin Zhu, Xinyu Wang +2
While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems withou…
NewsQuote: A Dataset Built on Quote Extraction and Attribution for Expert Recommendation in Fact-Checking
Wenjia Zhang, Lin Gui, Rob Procter +1
To enhance the ability to find credible evidence in news articles, we propose a novel task of expert recommendation, which aims to identify trustworthy experts on a specific news t…
Counterfactual Generation with Identifiability Guarantees
Hanqi Yan, Lingjing Kong, Lin Gui +4
Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires…
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
Junru Lu, Gabriele Pergola, Lin Gui +2
We introduce CHIME, a cross-passage hierarchical memory network for question answering (QA) via text generation. It extends XLNet introducing an auxiliary memory module consisting…
A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports
Xinyu Wang, Lin Gui, Yulan He
Table of contents (ToC) extraction centres on structuring documents in a hierarchical manner. In this paper, we propose a new dataset, ESGDoc, comprising 1,093 ESG annual reports f…
Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning
Chenghao Yang, Lin Gui, Chenxiao Yang +3
Reinforcement learning with verifiable rewards (RLVR) is a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs), yet its success hinges on eff…
AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction
Pollawat Hongwimol, Haoning Shang, Chutong Wang +6
Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language…
OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning
Jiazheng Li, Runcong Zhao, Yongxin Yang +2
The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive runnin…
MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
Yiming Du, Bingbing Wang, Yang He +7
Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities fo…
Explainable Recommender with Geometric Information Bottleneck
Hanqi Yan, Lin Gui, Menghan Wang +2
Explainable recommender systems can explain their recommendation decisions, enhancing user trust in the systems. Most explainable recommender systems either rely on human-annotated…
A Question Answering Approach to Emotion Cause Extraction
Lin Gui, Jiannan Hu, Yulan He +3
Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by r…
Cone: Unsupervised Contrastive Opinion Extraction
Runcong Zhao, Lin Gui, Yulan He
Contrastive opinion extraction aims to extract a structured summary or key points organised as positive and negative viewpoints towards a common aspect or topic. Most recent works…
Block Distributed Compressive Sensing Based Doubly Selective Channel Estimation and Pilot Design for Large-Scale MIMO Systems
Bo Gong, Lin Gui, Qibo Qin +2
The doubly selective (DS) channel estimation in the large-scale multiple-input multiple-output (MIMO) systems is a challenging problem due to the large number of the channel coeffi…
Clustering Based Hybrid Precoding Design for Multi-User Massive MIMO Systems
Ling Zhang, Lin Gui, Kai Ying +1
Hybrid precoding has been recognized as a promising technology to combat the path loss of millimeter wave signals in massive multiple-input multiple-output (MIMO) systems. However,…
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Han Zhang, Lin Gui, Yu Lei +8
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of…
COPR: Continual Learning Human Preference through Optimal Policy Regularization
Han Zhang, Lin Gui, Yuanzhao Zhai +3
The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to…
Statistical Inference for Cell Type Deconvolution
Dongyue Xie, Lin Gui, Jingshu Wang
Integrating heterogeneous datasets across different measurement platforms is a fundamental challenge in many scientific applications. A common example arises in deconvolution probl…
Structured Distributed Compressive Channel Estimation over Doubly Selective Channels
Qibo Qin, Lin Gui, Bo Gong +2
For an orthogonal frequency-division multiplexing (OFDM) system over a doubly selective (DS) channel, a large number of pilot subcarriers are needed to estimate the numerous channe…
Distilling ChatGPT for Explainable Automated Student Answer Assessment
Jiazheng Li, Lin Gui, Yuxiang Zhou +3
Providing explainable and faithful feedback is crucial for automated student answer assessment. In this paper, we introduce a novel framework that explores using ChatGPT, a cutting…
Correcting Large Language Model Behavior via Influence Function
Han Zhang, Zhuo Zhang, Yi Zhang +8
Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature…
Reconfigurable Intelligent Surface Deployment for Wideband Millimeter Wave Systems
Xiaohao Mo, Lin Gui, Kai Ying +2
The performance of wireless communication systems is fundamentally constrained by random and uncontrollable wireless channels. Recently, reconfigurable intelligent surfaces (RIS) h…
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang +3
Understanding in-context learning (ICL) capability that enables large language models (LLMs) to excel in proficiency through demonstration examples is of utmost importance. This im…
Aggregating Dependent Signals with Heavy-Tailed Combination Tests
Lin Gui, Yuchao Jiang, Jingshu Wang
Combining dependent p-values poses a long-standing challenge in statistical inference, particularly when aggregating findings from multiple methods to enhance signal detection. Rec…
Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies
Gabriele Pergola, Elena Kochkina, Lin Gui +2
Biomedical question-answering (QA) has gained increased attention for its capability to provide users with high-quality information from a vast scientific literature. Although an i…
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
Jiazheng Li, Yuxiang Zhou, Junru Lu +4
Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is pr…
Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
Siya Qi, Yudong Chen, Runcong Zhao +6
Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available du…
ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
Shao Wang, Rui Ren, Lin Gui
The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. Wh…
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models
Yanzheng Xiang, Hanqi Yan, Lin Gui +1
In-context learning has become a popular paradigm in natural language processing. However, its performance can be significantly influenced by the order of in-context demonstration…
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
Qinglin Zhu, Runcong Zhao, Hanqi Yan +3
Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that op…
SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
Zhenyi Shen, Junru Lu, Lin Gui +4
Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained m…
Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding Enhancement
Zipeng Zhu, Zhanghao Hu, Qinglin Zhu +5
Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to…
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
Qinglin Zhu, Yizhen Yao, Runcong Zhao +7
Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired app…
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
Runcong Zhao, Qinglin Zhu, Hainiu Xu +3
Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming an…
Tracking Brand-Associated Polarity-Bearing Topics in User Reviews
Runcong Zhao, Lin Gui, Hanqi Yan +1
Monitoring online customer reviews is important for business organisations to measure customer satisfaction and better manage their reputations. In this paper, we propose a novel d…
Recent Advances in Multimodal Affective Computing: An NLP Perspective
Guimin Hu, Weimin Lyu, Chang Sun +5
Multimodal affective computing has gained increasing attention due to its broad applications in understanding human behavior and intentions, particularly in text-centric multimodal…
PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA
Xinyu Wang, Yanzheng Xiang, Lin Gui +1
Long-document QA presents challenges with large-scale text and long-distance dependencies. Recent advances in Large Language Models (LLMs) enable entire documents to be processed i…
Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews
Runcong Zhao, Lin Gui, Gabriele Pergola +1
In this paper, we propose the Brand-Topic Model (BTM) which aims to detect brand-associated polarity-bearing topics from product reviews. Different from existing models for sentime…
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding
Lixing Zhu, Runcong Zhao, Lin Gui +1
Narrative understanding involves capturing the author's cognitive processes, providing insights into their knowledge, intentions, beliefs, and desires. Although large language mode…
Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages
Yuemei Xu, Kexin Xu, Jian Zhou +2
The current Large Language Models (LLMs) face significant challenges in improving their performance on low-resource languages and urgently need data-efficient methods without costl…
NarrativePlay: Interactive Narrative Understanding
Runcong Zhao, Wenjia Zhang, Jiazheng Li +4
In this paper, we introduce NarrativePlay, a novel system that allows users to role-play a fictional character and interact with other characters in narratives such as novels in an…
Hierarchical Interpretation of Neural Text Classification
Hanqi Yan, Lin Gui, Yulan He
Recent years have witnessed increasing interests in developing interpretable models in Natural Language Processing (NLP). Most existing models aim at identifying input features suc…
Detecting Multiple Replicating Signals using Adaptive Filtering Procedures
Jingshu Wang, Lin Gui, Weijie J. Su +2
Replicability is a fundamental quality of scientific discoveries: we are interested in those signals that are detectable in different laboratories, study populations, across time e…
PANACEA: An Automated Misinformation Detection System on COVID-19
Runcong Zhao, Miguel Arana-Catania, Lixing Zhu +6
In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection. Our fact-check…
Multi-Layer Ranking with Large Language Models for News Source Recommendation
Wenjia Zhang, Lin Gui, Rob Procter +1
To seek reliable information sources for news events, we introduce a novel task of expert recommendation, which aims to identify trustworthy sources based on their previously quote…
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
Hanqi Yan, Yanzheng Xiang, Guangyi Chen +3
To better interpret the intrinsic mechanism of large language models (LLMs), recent studies focus on monosemanticity on its basic units. A monosemantic neuron is dedicated to a sin…
A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews
Gabriele Pergola, Lin Gui, Yulan He
The flexibility of the inference process in Variational Autoencoders (VAEs) has recently led to revising traditional probabilistic topic models giving rise to Neural Topic Models (…
Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering
Junru Lu, Gabriele Pergola, Lin Gui +1
We propose a simple yet effective strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization to improve the event reasoning capab…
Causal Estimation for Text Data with (Apparent) Overlap Violations
Lin Gui, Victor Veitch
Consider the problem of estimating the causal effect of some attribute of a text document; for example: what effect does writing a polite vs. rude email have on response time? To e…
Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation
Junru Lu, Xingwei Tan, Gabriele Pergola +2
Human reading comprehension often requires reasoning of event semantic relations in narratives, represented by Event-centric Question-Answering (QA). To address event-centric QA, w…
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
Ang Li, Jingqian Zhao, Bin Liang +6
Stance detection is critical for understanding the underlying position or attitude expressed toward a topic. Large language models (LLMs) have demonstrated significant advancements…
CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models
Jiazheng Li, Zhaoyue Sun, Bin Liang +2
Text classifiers built on Pre-trained Language Models (PLMs) have achieved remarkable progress in various tasks including sentiment analysis, natural language inference, and questi…
Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection
Lixing Zhu, Gabriele Pergola, Lin Gui +2
Emotion detection in dialogues is challenging as it often requires the identification of thematic topics underlying a conversation, the relevant commonsense knowledge, and the intr…
Distributed Compressive Sensing Based Doubly Selective Channel Estimation for Large-Scale MIMO Systems
Bo Gong, Qibo Qin, Xiang Ren +3
Doubly selective (DS) channel estimation in largescale multiple-input multiple-output (MIMO) systems is a challenging problem due to the requirement of unaffordable pilot overheads…
Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
Shenzhi Yang, Bin Liang, An Liu +3
Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distributi…
Addressing Token Uniformity in Transformers via Singular Value Transformation
Hanqi Yan, Lin Gui, Wenjie Li +1
Token uniformity is commonly observed in transformer-based models, in which different tokens share a large proportion of similar information after going through stacked multiple se…