Papers by Wei Bi

Set Generation Networks for End-to-End Knowledge Base Population (2021.emnlp-main)

Challenge:	Existing evaluation metrics for open-domain dialogue systems are limited by the diversity of possible outcomings.
Approach:	They propose a method to augment a reference set to improve reliability . they propose BLEU to measure similarity between a predicted response and a small set of references .
Outcome:	The proposed model improves the reliability of reference-based metrics with augmented reference sets.

Copied to clipboard

Dianbo Sui, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, Wei Bi

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning (2025.emnlp-main)

Challenge:	Existing knowledge base population systems require a machine translation task to generate multiple facts, but the fact order is not considered.
Approach:	They propose a knowledge base population task that aims to discover facts about entities from texts and expand a KB with these facts.
Outcome:	The proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.

Copied to clipboard

Gangwei Jiang, Yahui Liu, Zhaoyi Li, Wei Bi, Fuzheng Zhang, Linqi Song, Ying Wei, Defu Lian

Reasoning

Challenge:	Recent advances in reasoning with large language models have popularized Long Chain-of-Thought (LCoT) a framework that converts sequential LCoTs into hierarchical tree structures enables deeper structural analysis of LLM reasoning.
Approach:	They propose a framework that converts sequential LCoTs into hierarchical tree structures and enables deeper structural analysis of LLM reasoning.
Outcome:	The proposed framework can be used to analyze LLM reasoning in a variety of tasks and models.

Event Transition Planning for Open-ended Text Generation (2022.findings-acl)

Copied to clipboard

Qintong Li, Piji Li, Wei Bi, Zhaochun Ren, Yuxuan Lai, Lingpeng Kong

Knowledge Verification to Nip Hallucination in the Bud (2024.emnlp-main)

Challenge:	Open-ended text generation tasks require models to generate coherent continuation given limited preceding context.
Approach:	They propose a novel two-stage method which explicitly arranges ensuing events in open-ended text generation tasks.
Outcome:	The proposed method improves coherence and diversity of open-ended text generation tasks.

Copied to clipboard

Fanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan, Wei Bi, Shuming Shi

Reasoning

Challenge:	Recent studies have shown that large language models generate responses that sound plausible but contradict factual knowledge, a phenomenon known as hallucination.
Approach:	They propose a novel approach to align large language models to evaluate knowledge boundaries based on external knowledge to reduce hallucinations .
Outcome:	The proposed approach reduces hallucinations across six benchmarks using foundation LLMs of varying backbones and scales.

TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching (2020.coling-main)

Copied to clipboard

Heng Gong, Yawei Sun, Xiaocheng Feng, Bing Qin, Wei Bi, Xiaojiang Liu, Ting Liu

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound (2026.acl-long)

Challenge:	Recent studies show that pre-trained language models can produce informative and fluent text with the help of large-scale datasets, but they suffer insufficient learning problem with limited training data.
Approach:	They propose to use table transformation module with template to rewrite structured table in natural language as input for GPT-2 and exploit multi-task learning with two auxiliary tasks to preserve table’s structural information.
Outcome:	The proposed model outperforms existing systems on most few-shot settings.

Copied to clipboard

Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui, Wei Bi, Song-Chun Zhu, Bo Zhao, Zilong Zheng

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

Challenge:	Humor enriches our daily lives and appears in many forms, from jokes and cartoons to comedies and viral videos.
Approach:	They introduce a video humor understanding benchmark to test their ability to understand humor from visual cues.
Outcome:	The proposed video humor understanding benchmark is based on a collection of short videos . it features rich annotations and a study of environmental sound that can enhance humor .

Copied to clipboard

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework (D19-1)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi

TRAMS: Training-free Memory Selection for Long-range Language Modeling (2023.findings-emnlp)

Challenge:	generative models for end-to-end sequence generation have been shown promising for this task . however, how to precisely extract a skeleton and how to effectively train a retrieval-guided response generator is still challenging.
Approach:	They propose a framework where skeleton extraction is made by an interpretable matching model and a retrieval-guided response generator is followed by a separate generator.
Outcome:	The proposed framework outperforms baseline models in a variety of experiments.

Copied to clipboard

Haofei Yu, Cunxiang Wang, Yue Zhang, Wei Bi

Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)

Challenge:	Existing methods like Transformer-XL are plagued by ineffective memory selections due to the high number of tokens involved in attention calculation.
Approach:	They propose a plug-and-play strategy that selects tokens participating in attention calculation based on one simple metric and ignores the other ones.
Outcome:	The proposed strategy keeps tokens with high attention scores and ignores the other ones on word-level and character-level benchmarks without additional training or adding additional parameters.

Copied to clipboard

Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Challenge:	Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping.
Approach:	They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis.
Outcome:	The proposed model outperforms baselines on real-world datasets.

Copied to clipboard

Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai

Information Retrieval

Challenge:	Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing.
Approach:	They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards.
Outcome:	The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations .

Psychology-guided Controllable Story Generation (2022.coling-1)

Copied to clipboard

Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing controllable story generation systems ignore the psychological changes of the protagonists and focus on the appointed keywords or emotions.
Approach:	They propose a Psychology-guided Controllable Story Generation System (PICS) that generates stories that adhere to the given leading context and desired psychological state chains for the protagonist.
Outcome:	The proposed system outperforms baselines and shows that it can generate stories with more consistent psychological changes.

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Information Retrieval

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation (2020.emnlp-main)

Copied to clipboard

Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

Incorporating External Knowledge into Machine Reading for Generative Question Answering (D19-1)

Challenge:	Existing techniques for natural language understanding and generation use autoencoding and/or autoregressive objectives to train models.
Approach:	They propose a self-supervised pre-training scheme that pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus for generating new text conditioned on context.
Outcome:	The proposed scheme achieves state-of-the-art results on a variety of language generation benchmarks covering generative question answering, abstractive summarization and conversational response generation.

Copied to clipboard

Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning (2025.coling-main)

Challenge:	Existing knowledge-aware QA models do not have commonsense and background knowledge to answer nontrivial questions.
Approach:	They propose a new neural model which exploits external knowledge to generate answers in natural language for a given question with context.
Outcome:	The proposed model improves answer quality over existing models without knowledge and knowledge-aware models, a study shows . state officials in Hawaii confirmed that president Barack Obama was born in the U.S.

Copied to clipboard

Jing Bi, Yuting Wu, Weiwei Xing, Zhenjie Wei

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective (2025.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks.
Approach:	They propose a new reasoning strategy Solution Guidance (SG) and a plug-and-play training paradigm Solution-Guidance Fine-Tuning (SGFT) which focuses on problem understanding and decomposition at the semantic and logical levels, rather than specific computations.
Outcome:	The proposed reasoning strategy Solution Guidance (SG) and plug-and-play training paradigm Solution-Guidance Fine-Tuning (SGFT) improves the reasoning capabilities of small language models on various reasoning tasks.

Copied to clipboard

Yuchen Wen, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	Existing studies have shown that large language models (LLMs) can elicit implicit biases that hurt certain demographics without explicit harmful words.
Approach:	They propose three attack approaches to elicit agreements to biased viewpoints from LLMs from a psychometric perspective and built two benchmarks to compare them.
Outcome:	The proposed methods elicit agreements to biased viewpoints more effectively than baselines.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models (2024.findings-acl)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong

Automatic Article Commenting: the Task and Dataset (P18-2)

Challenge:	Multimodal reasoning is a key capability for large vision-language models . however, the vanilla Chain-of-Thought method fails to address critical steps in multi-step reasoning tasks.
Approach:	They propose a bi-modal Behavioral Alignment method to augment multimodal reasoning . they use domain-specific language to integrate multimodal information into a precise alternative form .
Outcome:	The proposed method significantly improves GPT-4V(ision) on geometry problem solving, chess positional advantage prediction and molecular property prediction.

Copied to clipboard

Lianhui Qin, Lemao Liu, Wei Bi, Yan Wang, Xiaojiang Liu, Zhiting Hu, Hai Zhao, Shuming Shi

Challenge:	Existing methods to make comments on articles are based on human-annotated subsets, but they are not suitable for online forums.
Approach:	They propose to use a large-scale Chinese corpus with millions of real comments and a human-annotated subset characterizing the comments’ varying quality to generalize a broad set of popular reference-based metrics.
Outcome:	The proposed model incorporates human-annotated subset characterizing the comments’ varying quality and shows that it is more accurate than previous models.

Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning (2020.findings-emnlp)

Copied to clipboard

Yifan Gao, Piji Li, Wei Bi, Xiaojiang Liu, Michael Lyu, Irwin King

COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities (2022.coling-1)

Challenge:	Sentence function is an important linguistic feature indicating the communicative purpose of a sentence in a conversation.
Approach:	They propose a structured meta-learning approach for dialogue generation on infrequent sentence functions.
Outcome:	The proposed approach improves informativeness and relevance of dialogue generation on infrequent sentence functions while preserving knowledge generalization for similar sentence functions.

Copied to clipboard

Yuqiang Xie, Yue Hu, Wei Peng, Guanqun Bi, Luxi Xing

Challenge:	Existing methods for modeling motivations, emotions and actions in language-based human activities have been limited.
Approach:	They propose to model motivations, emotions and actions in language-based human activities using a dataset called Story Commonsense.
Outcome:	The proposed model can better reveal the essential relationship between motivations, emotions and actions than existing methods.

Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)

Copied to clipboard

Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi

Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method (D18-1)

Challenge:	Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs).
Approach:	They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD).
Outcome:	The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation.

Copied to clipboard

Yahui Liu, Wei Bi, Jun Gao, Xiaojiang Liu, Jian Yao, Shuming Shi

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks (2025.coling-main)

Challenge:	Experimental results show that Sequence-to-sequence models tend to generate generic/dull responses .
Approach:	They propose a statistical re-weighting method that assigns different weights for multiple responses of the same query.
Outcome:	The proposed method improves acceptance rate of generated responses and significantly reduces generated generic responses.

Copied to clipboard

Qintong Li, Leyang Cui, Lingpeng Kong, Wei Bi

A Frustratingly Simple Decoding Method for Neural Text Generation (2024.lrec-main)

Challenge:	Existing work uses large language models (LLMs) to evaluate natural language process tasks, but there are shortcomings in current LLMs.
Approach:	They examine the alignment between LLM evaluators and human annotators by comparing conventional and alignment tasks with different evaluation criteria.
Outcome:	The proposed models excel in general criteria, such as fluency, but face challenges with complex criteria, including numerical reasoning.

Copied to clipboard

Haoran Yang, Deng Cai, Huayang Li, Wei Bi, Wai Lam, Shuming Shi

Pretrained Language Models for Dialogue Generation with Multiple Input Sources (2020.findings-emnlp)

Challenge:	Neural text generation is notorious for repetitive loops and tedious outputs.
Approach:	They propose a method that penalizes future generation of repetitive content . they construct an anti-LM based on previously generated text .
Outcome:	The proposed method outperforms established baselines in terms of generation quality, decoding speed, and universality.

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Dacheng Tao

Spotting AI’s Touch: Identifying LLM-Paraphrased Spans in Text (2024.findings-acl)

Challenge:	Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks.
Approach:	They propose to fuse attention information from multiple input sources to achieve better relevance with dialogue history than simple fusion baselines.
Outcome:	The proposed models deliver higher relevance with dialogue history than baselines.

Copied to clipboard

Yafu Li, Zhilin Wang, Leyang Cui, Wei Bi, Shuming Shi, Yue Zhang

LLM-Based Multi-Agent Systems are Scalable Graph Generative Models (2025.findings-acl)

Challenge:	Existing work focuses on detecting (partially) AI-generated texts, but paraphrasing is commonly employed in various application scenarios for text refinement and diversity.
Approach:	They propose a framework for paraphrased text span detection that takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.
Outcome:	The proposed framework can detect paraphrased text spans within a text . it takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.

Copied to clipboard

Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding

Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021.acl-short)

Challenge:	Social graphs are mathematical structures stem from pairwise interactions between entities through nodes and edges.
Approach:	They propose a framework for dynamic, text-attributed social graph generation that simulates the temporal node and edge generation processes for zero-shot social graphs.
Outcome:	The proposed framework improves macroscopic graph structure metrics by 11% . the proposed model can generate graphs with up to 100,000 nodes or 10 million edges .

Copied to clipboard

Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers (2024.acl-long)

Challenge:	Recent work focuses on question answering based on machine reading comprehension . current approaches treat QA as extracting a consecutive piece of text to a given question.
Approach:	They propose a generative QA model that incorporates an extractive mechanism into a model.
Outcome:	The proposed model improves quality and semantic accuracy over baseline models.

Copied to clipboard

Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, Wei Bi

Data Augmentation for Text Generation Without Any Augmented Data (2021.acl-long)

Challenge:	Large language models (LLMs) have demonstrated impressive performance across various mathematical reasoning benchmarks.
Approach:	They introduce an adversarial grade school math dataset and explore whether LLMs can be more robust when questions are slightly changed.
Outcome:	The proposed method generates and verifies each intermediate thought based on its reasoning goal and calculation result.

Copied to clipboard

Wei Bi, Huayang Li, Jiacheng Huang

Event Extraction as Machine Reading Comprehension (2020.emnlp-main)

Challenge:	Existing methods for data augmentation need to define or choose proper data mapping functions to create augmented samples.
Approach:	They propose to use data mapping functions to augment text samples without using specific mapping functions.
Outcome:	The proposed approach can approximate or even surpass popular data augmentation methods on two text generation tasks with a convergence rate guarantee.

Copied to clipboard

Jian Liu, Yubo Chen, Kang Liu, Wei Bi, Xiaojiang Liu

Information Extraction & Text Mining

Challenge:	Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts.
Approach:	They propose a new learning paradigm for event extraction by explicitly casting it as a machine reading comprehension problem.
Outcome:	The proposed model achieves state-of-the-art performance on the data-scarce scenario, achieving 49.8% in F1 for event argument extraction with only 1% data, compared with 2.2% of the previous method.

Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration (2023.emnlp-main)

Copied to clipboard

Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi

RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation (2023.emnlp-main)

Challenge:	Existing data for instruction-tuning are inadequate for a wide range of tasks, limiting the scope for nuanced comprehension and interactions within these domains.
Approach:	They propose to use Large Language Models to explore a multitude of variations or possibilities to improve instruction-tuning data by active exploration.
Outcome:	The proposed approach improves domain-specific instruction coverage and shows significant improvements over baselines.

Copied to clipboard

Yue Zhang, Leyang Cui, Enbo Zhao, Wei Bi, Shuming Shi

Robustness in NLP

Challenge:	Grammatical Error Correction (GEC) systems perform well in academic benchmarks, but in practical applications they may not correct errors when users perform irrelevant modifications.
Approach:	They propose a benchmark to evaluate the context robustness of Grammatical Error Correction systems.
Outcome:	The proposed method improves the accuracy of errors corrected by human annotations.

Pre-training Multi-party Dialogue Models with Latent Discourse Inference (2023.acl-long)

Copied to clipboard

Yiyang Li, Xinting Huang, Wei Bi, Hai Zhao

DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral (2025.acl-demo)

Challenge:	Existing studies have failed to scale up the pre-training process by putting aside unlabeled data . et al., 2019: multi-party dialogues are more difficult for models to understand since they involve multiple interlocutors resulting in interweaving reply-to relations and information flows.
Approach:	They propose to treat discourse structures as latent variables and jointly infer them to pre-train a model that understands the discourse structure of multi-party dialogues.
Outcome:	The proposed model outperforms baselines and achieves state-of-the-art results on multiple downstream tasks.

Copied to clipboard

Qiang Sun, Sirui Li, Tingting Bi, Du Q. Huynh, Mark Reynolds, Yuanyi Luo, Wei Liu

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Challenge:	Documents that are image-based are difficult to extract because of document variability.
Approach:	They propose a human-in-the-spiral assistive document annotation platform to extract structured data from document collections.
Outcome:	The proposed framework reduces annotation time by at least 41% while showing consistent performance gains over three iterations.

Copied to clipboard

Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

SAM3-I: Segment Anything with Instructions (2026.acl-long)

Challenge:	Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach:	They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome:	The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Copied to clipboard

Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng

Low-Resource NLP

Challenge:	Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering.
Approach:	They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework.
Outcome:	Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability.

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation (2021.acl-long)

Copied to clipboard

Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory (N19-1)

Challenge:	Recent studies report improvements when equipping models with multimodal information, but it remains unclear whether such improvements actually come from the multimodal part.
Approach:	They propose to extend conventional text-only translation models with multimodal information by extending them with visual input.
Outcome:	The proposed models replicate similar gains as recently developed multimodal-integrated systems achieved, but learn to ignore multimodal information.

Copied to clipboard

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi

Explanation Regeneration via Information Bottleneck (2023.findings-acl)

Challenge:	Existing generative dialogue models generate responses from input queries . however, the results are limited and the models are unsatisfactory .
Approach:	They propose a framework which exploits retrieval results via a skeleton-to-response paradigm . they extract a query skelet and use it to generate a new skele and response .
Outcome:	The proposed approach significantly improves the informativeness of the generated responses.

Copied to clipboard

Qintong Li, Zhiyong Wu, Lingpeng Kong, Wei Bi

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Challenge:	Recent work builds on prompt engineering to generate free-text explanations without specific training, but they lack sufficiency and conciseness due to the prompt complexity and hallucination issues.
Approach:	They propose to generate explanations via the information bottleneck theory by polishing the single-pass output of large pretrained language models but retaining the information that supports the contents being explained by balancing two information bottle neck objectives.
Outcome:	The proposed explanations are based on the information bottleneck theory . they are able to explain black-box predictions naturally and accurately .

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao

Unsupervised Rewriter for Multi-Sentence Compression (P19-1)

Challenge:	Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach:	They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome:	The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

Copied to clipboard

Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa

Effidit: An Assistant for Improving Writing Efficiency (2023.acl-demo)

Challenge:	Multi-sentence compression aims to generate a grammatical but reduced compression from multiple input sentences while retaining key information.
Approach:	They propose a neural rewriter for multi-sentence compression that does not need any parallel corpus.
Outcome:	Empirical studies show that the proposed approach achieves comparable results upon automatic evaluation and improves the grammaticality of compression based on human evaluation.

Copied to clipboard

Shuming Shi, Enbo Zhao, Wei Bi, Deng Cai, Leyang Cui, Xinting Huang, Haiyun Jiang, Duyu Tang, Kaiqiang Song, Longyue Wang, Chenyan Huang, Guoping Huang, Yan Wang, Piji Li

Green & Sustainable NLP

Challenge:	Effidit is a digital writing assistant that provides three modules to help users write faster and more efficiently.
Approach:	They present Effidit, a digital writing assistant that provides three modules to help users write higher-quality text more efficiently.
Outcome:	Effidit expands the capabilities of a typical writing assistant by providing three modules . Effit can help users create their own text faster and more efficiently .

Instruction Pre-Training: Language Models are Supervised Multitask Learners (2024.emnlp-main)

Copied to clipboard

Daixuan Cheng, Yuxian Gu, Shaohan Huang, Junyu Bi, Minlie Huang, Furu Wei

Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References (P19-1)

Challenge:	Unsupervised multitask pre-training has been the key to the success of language models (LMs) however, scaling it in the post-training stage trends towards better generalization.
Approach:	They propose a framework that augments massive raw corpora with instruction-response pairs to pre-train LMs.
Outcome:	The proposed framework augments massive raw corpora with instruction-response pairs to pre-train LMs.

Copied to clipboard

Lisong Qiu, Juntao Li, Wei Bi, Dongyan Zhao, Rui Yan

Explicit Syntactic Guidance for Neural Text Generation (2023.acl-long)

Challenge:	Existing approaches to open-domain dialogue generation ignore the nature of 1-to-1 mapping that there may exist multiple valid responses corresponding to the same query.
Approach:	They propose to model open-domain dialogue generation using 1-to-1 mapping . they first extract common features of different responses and then combine them with distinctive features to generate multiple diverse and appropriate responses.
Outcome:	The proposed model outperforms existing models on automatic and human evaluations.

Copied to clipboard

Yafu Li, Leyang Cui, Jianhao Yan, Yongjing Yin, Wei Bi, Shuming Shi, Yue Zhang

Syntactic Text Processing

Challenge:	Existing text generation models follow the sequence-to-sequence paradigm . generative grammar suggests humans generate language by learning language grammar .
Approach:	They propose a syntax-guided generation schema that searches the syntax tree in a top-down direction.
Outcome:	The proposed method outperforms autoregressive baselines on paraphrase generation and machine translation.

MAGE: Machine-generated Text Detection in the Wild (2024.acl-long)

Copied to clipboard

Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, Yue Zhang

Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (2023.emnlp-main)

Challenge:	Existing research has focused on evaluating detection methods for specific domains or language models.
Approach:	They build a testbed to detect texts from diverse human writings and LLMs using different detection methods.
Outcome:	Empirical results show that the top performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.

Copied to clipboard

Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, Wei Bi

Lexical Knowledge Internalization for Neural Dialog Generation (2022.acl-long)

Challenge:	generative models struggle to distinguish subtle differences among retrieved knowledge records, resulting in suboptimal quality of generated responses.
Approach:	They propose to use maximum marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision.
Outcome:	The proposed approach improves on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models.

Copied to clipboard

Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao

AutoDSL: Automated domain-specific language design for structural representation of procedures with constraints (2024.acl-long)

Challenge:	Existing knowledge-grounded dialog models ignore the knowledge that resides in people's minds during a conversation.
Approach:	They propose to integrate lexical knowledge internally into the model's parameters instead of further conditioning them on external knowledge . they adopt contrastive learning approach and use a dictionary-based token-level lexicon retriever that requires only weak supervision.
Outcome:	The proposed model can relate J.K Rowling to Khalsa Aid with the knowledge retrieved from Wikipedia.

Copied to clipboard

Yu-Zhe Shi, Haofei Hou, Zhangqian Bi, Fanxu Meng, Xiang Wei, Lecheng Ruan, Qining Wang

A Batch Normalized Inference Network Keeps the KL Vanishing Away (2020.acl-main)

Challenge:	Domain-specific Language (DSL) is an effective tool to express constraints structurally, but requires case-by-case hand-crafting.
Approach:	They propose a framework to automate domain-specific language constraint design . they propose 'autoDSL' framework to optimize syntactic and semantic constraints .
Outcome:	The framework automates constraint design across domains and abstracts semantic constraints.

Copied to clipboard

Qile Zhu, Wei Bi, Xiaojiang Liu, Xiyao Ma, Xiaolin Li, Dapeng Wu

Challenge:	Variational Autoencoder (VAE) is widely used to approximate a model’s posterior on latent variables.
Approach:	They propose to let the Kullback–Leibler divergence individual follow a distribution across the whole dataset and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL’s distribution positive.
Outcome:	The proposed approach can avoid posterior collapse effectively and efficiently without introducing any new model component or modifying the objective.

StructuralLM: Structural Pre-training for Form Understanding (2021.acl-long)

Copied to clipboard

Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation (2023.findings-eacl)

Challenge:	Existing pre-trained language models focus on text-only representation, neglecting cell-level layout information.
Approach:	They propose a pre-training approach to leverage cell and layout information from scanned documents.
Outcome:	The proposed model achieves state-of-the-art in various downstream tasks . it uses 2Dposition embeddings to model word-level layout information .

Copied to clipboard

Haoran Yang, Yan Wang, Piji Li, Wei Bi, Wai Lam, Chen Xu

Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog (2023.acl-long)

Challenge:	Existing methods focusing on this task usually concatenate the concatened concepts words as the inputs of a pre-trained language model (PLM) however, in pre-training, the input is often corrupted sentences with correct word order.
Approach:	They propose a two-stage framework to improve the ability of pre-trained language models to deal with masked sentences with incorrect word order and a special token to make the input distribution more similar to the one used in pre-training.
Outcome:	The proposed method is able to generate a sentence containing all given concepts and correctly describe the relations between concepts.

Copied to clipboard

Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan, Wei Bi

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Challenge:	Existing systems blend knowledge retrieval with response generation and optimize them with direct supervision from reference responses.
Approach:	They propose a multi-grained knowledge retrieval system that decouples knowledge retrievals from response generation and introduces an entity selector and an attribute selector to acquire multigrained information from the knowledge base.
Outcome:	The proposed system performs better on small and large knowledge bases.

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Visual Data in NLP

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

A Discrete CVAE for Response Generation on Short-Text Conversation (D19-1)

Copied to clipboard

Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Guodong Zhou, Shuming Shi

Fine-Grained Sentence Functions for Short-Text Conversation (P19-1)

Challenge:	Neural conversation models are easy to generate bland and generic responses . however, their improvement of generating high-quality responses is still unsatisfactory .
Approach:	They propose to use a discrete latent variable with an explicit semantic meaning to improve the conditional variational autoencoder on short-text conversation.
Outcome:	The proposed model outperforms various kinds of generation models under automatic and human evaluations and generates more diverse and informative responses.

Copied to clipboard

Wei Bi, Jun Gao, Xiaojiang Liu, Shuming Shi

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)

Challenge:	Existing research has analyzed various factors indicating the conversational purpose such as emotions, topics, word orders, syntactic patterns and other aspects.
Approach:	They propose to annotate a short-text conversation dataset with annotated sentences and train conversation models conditioned on the sentence functions.
Outcome:	The proposed model can predict the quality of the returned responses.

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang

OpenUE: An Open Toolkit of Universal Extraction from Text (2020.emnlp-demos)

Challenge:	Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization.
Approach:	They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input.
Outcome:	The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs.

Copied to clipboard

Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei Zhang, Huajun Chen

Information Extraction & Text Mining

Challenge:	a large number of natural language processing tasks focus on token-level or sentence-level understandings.
Approach:	They propose an open-source and extensible toolkit for various extraction tasks . they deploy an online demo with restful APIs to support real-time extraction .
Outcome:	The proposed model can be used to extract information from text without training and deployment.

Learning to Abstract for Memory-augmented Conversational Response Generation (P19-1)

Copied to clipboard

Zhiliang Tian, Wei Bi, Xiaopeng Li, Nevin L. Zhang

TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection (2022.emnlp-main)

Challenge:	Existing generative models for open-domain chit-chat conversations lack informativeness and diversity.
Approach:	They propose a retrieval-augmented generative model that learns to abstract from the training corpus and saves useful information to the memory to assist the response generation.
Outcome:	The proposed model outperforms other baselines in query-response clustering and learning to utilize these characteristics for response generation.

Copied to clipboard

Chaoya Jiang, Haiyang Xu, Chenliang Li, Ming Yan, Wei Ye, Shikun Zhang, Bin Bi, Songfang Huang

Visual Data in NLP

Challenge:	Existing vision-and-language pre-training models suffer from long visual sequences . experimental results show that TRIPS gains a speedup of 40% over previous similar VLP models .
Approach:	They propose an efficient vision-and-language pre-training model with text-relevant image patch selection, TRIPS, which reduces the visual sequence progressively with a text-guided patch-selection layer in the visual backbone for efficient training and inference.
Outcome:	The proposed model can speed up training and inference by 40% over previous models.

Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression (2026.findings-acl)

Copied to clipboard

Haiyang Sun, Chenyang Le, Wei Wang, Leying Zhang, Chuang Li, Bing Han, Chenda Li, Mengxiao Bi, Yanmin Qian

SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving (2024.acl-long)

Challenge:	Existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect.
Approach:	They propose to use a large-scale, context-aware speech corpus derived from multi-speaker audiobooks to generate a speech that is human-like.
Outcome:	The proposed model outperforms existing methods in terms of emotional expression accuracy and naturalness.

Copied to clipboard

Xueliang Zhao, Xinting Huang, Wei Bi, Lingpeng Kong

Numerical Reasoning

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, including mathematical problem-solving.
Approach:	They propose a framework that connects the subgoal breakdown process and the probability of solving problems by identifying better subgoals with theoretical guarantees.
Outcome:	The proposed framework outperforms existing methods on two benchmarks, GSM8K and MATH, highlighting the potential of SEGO in AI-driven mathematical problem-solving.

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation (2020.acl-main)

Copied to clipboard

Zhiliang Tian, Wei Bi, Dongkyu Lee, Lanqing Xue, Yiping Song, Xiaojiang Liu, Nevin L. Zhang

On Synthetic Data for Back Translation (2022.naacl-main)

Challenge:	Neural conversation models generate appropriate but non-informative responses in general.
Approach:	They propose to construct a document memory with anticipated responses in mind using a teacher-student framework and a student's input.
Outcome:	The proposed model outperforms the state-of-the-art for the Conversing by Reading task.

Copied to clipboard

Jiahao Xu, Yubin Ruan, Wei Bi, Guoping Huang, Shuming Shi, Lihui Chen, Lemao Liu

Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification (2020.findings-emnlp)

Challenge:	Existing studies on back translation (BT) focus on beam search or random sampling . a new method to generate synthetic data with a backward model is proposed to improve BT performance.
Approach:	They propose a method to generate synthetic data to trade off quality and importance factors . back translation (BT) is one of the most significant technologies in NMT research fields .
Outcome:	The proposed method outperforms the baseline methods on WMT14 DE-EN, EN-DE, and RU-EN benchmark tasks.

Copied to clipboard

Heng Gong, Wei Bi, Xiaocheng Feng, Bing Qin, Xiaojiang Liu, Ting Liu

DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)

Challenge:	Table-to-text models that select and order salient data and verbalize them fluently are lacking in content planning stage.
Approach:	They propose to enhance neural content planning by understanding data values with contextual numerical value representations that bring the sense of value comparison into content planning.
Outcome:	The proposed model outperforms existing systems with respect to content planning metrics on ROTOWIRE and MLB datasets.

Copied to clipboard

Qian Cao, Yahui Liu, Wei Bi, Yi Zhao, Ruihua Song, Xiting Wang, Ruiming Tang, Guorui Zhou, Han Li

Challenge:	Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity.
Approach:	They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation.
Outcome:	The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories.

Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks (2020.acl-main)

Copied to clipboard

Yiping Song, Zequn Liu, Wei Bi, Rui Yan, Ming Zhang

VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation (2021.acl-long)

Challenge:	Existing methods for training generative models with minimal corpus are difficult . fine-tuning distinguishes tasks from parameter perspective but ignores model-structure perspective .
Approach:	They propose an algorithm that can customize a unique dialogue model for each task in the few-shot setting.
Outcome:	The proposed method outperforms baselines on two datasets in task consistency, response quality, diversity and consistency.

Copied to clipboard

Fuli Luo, Wei Wang, Jiahao Liu, Yijia Liu, Bin Bi, Songfang Huang, Fei Huang, Luo Si