Papers by Lu Cheng
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (2025.emnlp-main)
Copied to clipboard
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang
| Challenge: | Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions. |
| Approach: | They propose a data organization paradigm where large language models transform documents into more structured and loosely interconnected LUs. |
| Outcome: | Experiments in open-domain and industrial settings show that the proposed paradigm outperforms existing paradigms and shows high adaptability across diverse document formats. |
RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to mitigate hallucinations generate erroneous or fabricated information. |
| Approach: | They propose a rank-response-based model that annotates pair-reponses and trains alignment algorithms to improve the correspondence between images and text. |
| Outcome: | The proposed model outperforms the DPO method and outperfies existing methods on two MLLMs of different sizes and four widely used benchmarks. |
Partner Personas Generation for Dialogue Response Generation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing frameworks that focus on self personas ignore the value of partner persona . experimental results show that our framework generates relevant, interesting, coherent and informative partner personages even compared to ground truth partner personagers. |
| Approach: | They propose a framework that leverages automatic partner personas generation to enhance dialogue response generation. |
| Outcome: | The proposed framework generates relevant, interesting, coherent and informative partner personas even compared to ground truth partner person . it surpasses baselines that condition on ground truth persona . |
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)
Copied to clipboard
Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun
| Challenge: | Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language. |
| Approach: | They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking. |
| Outcome: | The proposed approach mitigates language bias and consistently improves mRAG performance across languages. |
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025.naacl-long)
Copied to clipboard
Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang
| Challenge: | Existing studies have shown that LLMs struggle to identify the boundaries of their own knowledge and tend to prioritize external information over internal knowledge learned during pre-training. |
| Approach: | They conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. |
| Outcome: | The proposed classifiers improve performance even when dealing with noisy knowledge databases. |
Few-Shot Multimodal Named Entity Recognition Based on Mutlimodal Causal Intervention Graph (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for multimodal named entity recognition are limited due to limited resources. |
| Approach: | They propose a Few-shot Multimodal Named Entity Recognition task to address these relation types by constructing a multimodal graph and a new multimodal causal intervention strategy. |
| Outcome: | The proposed model improves on two multimodal named entity recognition datasets. |
SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness (2026.acl-long)
Copied to clipboard
Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao
| Challenge: | SDiaReward is an end-to-end spoken dialogue system that integrates paralinguistic nuances and spontaneous nature of human conversation. |
| Approach: | They propose an end-to-end multi-turn reward model trained on SDiaReward-Dataset . it is a collection of episode-level preference pairs targeting modality and colloquiality gaps . |
| Outcome: | The proposed model outperforms general-purpose audio LLMs in episode-level evaluation. |
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. |
| Approach: | They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models. |
| Outcome: | The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts. |
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)
Copied to clipboard
Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu
| Challenge: | Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature. |
| Approach: | They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management. |
| Outcome: | The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench. |
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on retrieval-augmented generation (RAG) rarely address the issue of predictive uncertainty, i.e., how likely it is that a RAG model’s prediction is incorrect. |
| Approach: | They propose a framework that induces RAG models to alter latent factors and analyzes the effect on their answers. |
| Outcome: | The proposed framework identifies two critical factors affecting RAG models' confidence in their answers and analyzes the effect on their answers. |
Unsupervised Learning of Hierarchical Conversation Structure (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Goal-oriented conversations often have sub-dialogue structure, but it can be domain-dependent . Increasingly, language understanding applications involve conversational speech and text . |
| Approach: | They propose an unsupervised approach to learning hierarchical conversation structure . they use turn and sub-dialogue segment labels to decode the structure based on dialogue acts and subtasks . |
| Outcome: | The proposed approach improves neural models for three conversation-level understanding tasks. |
Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining (2026.findings-acl)
Copied to clipboard
| Challenge: | Conformal prediction (CP) has shown promise in offering correctness guarantees for LLMs, but it faces major challenges in continual domain pretraining (CDP). |
| Approach: | They propose an adaptive rejection and non-exchangeable CP framework that allows the LLM to selectively abstain from answering when its confidence or competence shifts significantly. |
| Outcome: | Experiments show that the proposed framework improves performance under continuous domain pretraining scenarios. |
Breaking the Noise Barrier: LLM-Guided Semantic Filtering and Enhancement for Multi-Modal Entity Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multimodal knowledge graphs. |
| Approach: | They propose a novel LLMguided MMEA framework that prioritizes noise reduction before fusion. |
| Outcome: | The proposed framework prioritizes noise reduction before fusion and improves semantics on the noisy FB YG dataset. |
From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics for large language models yield numerical scores that ignore user experience. |
| Approach: | They propose a metric that suggests revision edits that mimic the human writing process . their results show that the metric offers more insightful feedback and distinguishes between texts . |
| Outcome: | The proposed metric can provide a self-explained text evaluation result in a human-understandable manner beyond the context-independent score. |
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models (2024.findings-emnlp)
Copied to clipboard
Jiale Cheng, Yida Lu, Xiaotao Gu, Pei Ke, Xiao Liu, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Large Language Models (LLMs) exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks. |
| Approach: | They propose a framework to automatically expose weaknesses in Large Language Models (LLMs) they use three LLM-powered agents to perform comprehensive weakness identification . |
| Outcome: | The proposed framework shows that it is more effective than untargeted data augmentation methods like Self-Instruct to identify weaknesses in LLMs. |
DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation (2025.findings-naacl)
Copied to clipboard
Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu
| Challenge: | Text-to-image (T2I) generation models have advanced in recent years, but effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation. |
| Approach: | They propose to use off-the-shelf MLLMs and T2I models to build a multi-modal interactive dialogue system (MIDS) that can generate correct output modalities and coherence of output images. |
| Outcome: | The proposed pipeline can generate correct output modalities and coherent multi-modal outputs compared with other state-of-the-art models. |
Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun
| Challenge: | Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence. |
| Approach: | They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary. |
| Outcome: | Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training. |
ATGL: An Adaptive-Threshold Global Loss for Document-level Relation Extraction (2026.acl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) aims to determine which relations hold between a given entity pair in a document. |
| Approach: | They propose a document-level relation extraction paradigm that decouples existing losses into independent positive and negative losses, which interact solely with a shared threshold. |
| Outcome: | The proposed model outperforms existing models on four datasets and achieves state-of-the-art results. |
Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs. |
| Approach: | They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options . |
| Outcome: | The proposed framework reduces the number of options and improves on four datasets. |
Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to compress long contexts have degraded dramatically as compression ratios increase, sometimes even falling to the closed-book level. |
| Approach: | They propose a query-guided compression method that preserves key information within the compressed context. |
| Outcome: | The proposed method can consistently perform well even at high compression ratios, and offers significant benefits in terms of inference cost and throughput. |
A Set Prediction Network For Extractive Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent approaches to extracting salient sentences from source document are naive and lack dependencies between sentences. |
| Approach: | They propose a set prediction network to detect redundancy relationship between sentences . they use a non-autoregressive decoder to predict sentences in parallel . |
| Outcome: | The proposed method outperforms previous state-of-the-art models on extracted summary datasets. |
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training. |
| Approach: | They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack . |
| Outcome: | The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations. |
Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs (2025.naacl-long)
Copied to clipboard
| Challenge: | Randomly concatenating data points can lead to cross-contamination due to the significant difference in their subject matter. |
| Approach: | They propose a method that randomly concatenates data of varying lengths until reaching the designed maximum length to optimize context length and reduce padding. |
| Outcome: | The proposed method significantly improves performance on GSM8K and HumanEval, and also improves fairness and accuracy by 15%. |
Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring via Constructing the Optimal Subgraph of Demonstrations and Prompts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Using large language models as chatbots can cause hallucinations and lack of empathy, authors report . a dimension-agnostic scoring method is proposed to improve the performance of chatbot performance . |
| Approach: | They propose a dimension-agnostic scoring method that leverages in-context learning . they propose to automatically generate prompts and then request the LLM multiple times . |
| Outcome: | The proposed method outperforms baselines on five datasets. |
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Vision-Language Models have demonstrated remarkable capabilities in processing both visual and textual information. |
| Approach: | They examine the challenge of alignment and misalignment in LVLMs through an explainability lens. |
| Outcome: | The findings highlight the need for standardized evaluation protocols and in-depth explainability studies. |
EasyEA: Large Language Model is All You Need in Entity Alignment Between Knowledge Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Entity alignment (EA) aims to identify entities in different knowledge graphs (KGs) that represent the same real-world object. |
| Approach: | They propose an end-to-end EA framework based on large language models that requires no training to implement. |
| Outcome: | The proposed framework significantly reduces the reliance on seed entity pairs while achieving state-of-the-art (SOTA) performance on diverse datasets. |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)
Copied to clipboard
Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu
| Challenge: | Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios . |
| Approach: | They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios. |
| Outcome: | The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm. |
Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating complex semantics and diverse equations are limited by a fixed view. |
| Approach: | They propose a multi-view consistent contrastive learning approach that decouples human reasoning into two independent but consistent views. |
| Outcome: | The proposed approach significantly outperforms existing baselines on complex problems on multiple languages. |
AdvAug: Robust Adversarial Augmentation for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work in neural machine translation has led to dramatic improvements in both research and commercial systems. |
| Approach: | They propose a adversarial augmentation method for Neural Machine Translation that minimizes vicinal risk over virtual sentences . they use a novel vicinity distribution for adversarials to describe a smooth interpolated embedding space . |
| Outcome: | The proposed method outperforms the current method on Chinese-English, English-French, and English-German translation benchmarks. |
Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on complex questions does not consider controlling complexity of generated questions. |
| Approach: | They propose an end-to-end neural complexity-controllable question generation model that incorporates a mixture of experts as the selector of soft templates to capture question similarity while avoiding the expensive construction of actual templates. |
| Outcome: | The proposed model is superior to state-of-the-art methods in both automatic and manual evaluations on two benchmark QA datasets. |
SAM3-I: Segment Anything with Instructions (2026.acl-long)
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
| 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. |
TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route (2025.emnlp-main)
Copied to clipboard
Hongyi Luo, Qing Cheng, Daniel Matos, Hari Krishna Gadi, Yanfeng Zhang, Lu Liu, Yongliang Wang, Niclas Zeller, Daniel Cremers, Liqiu Meng
| Challenge: | Existing studies on large language models have limited evaluation of their geospatial cognition . a unified framework for evaluating geospcial cognition in LLMs remains absent . |
| Approach: | They propose a benchmark to evaluate the geospatial route cognition of Large Language Models . they propose 'pathbuilder' tool for converting natural language instructions into navigation routes . |
| Outcome: | The proposed framework and metrics evaluate 9 state-of-the-art LLMs on route reversal task. |
Debiasing Word Embeddings with Nonlinear Geometry (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for debiasing word embeddings are limited to individual social categories . however, real-world corpora typically present multiple social categories that may correlate or intersect with each other. |
| Approach: | They propose a method to debias word embeddings using nonlinear geometry of individual biases. |
| Outcome: | Empirical results show that the proposed method mitigates biases associated with individual social categories and treats each category in isolation. |
Learning Global Controller in Latent Space for Parameter-Efficient Fine-Tuning (2024.acl-long)
Copied to clipboard
Zeqi Tan, Yongliang Shen, Xiaoxia Cheng, Chang Zong, Wenqi Zhang, Jian Shao, Weiming Lu, Yueting Zhuang
| Challenge: | Large language models (LLMs) have shown remarkable performance, but their training costs are exorbitant. |
| Approach: | They propose a parameter-efficient method for exploring optimal solutions within latent space by using latent units to extract input representations from LLMs. |
| Outcome: | The proposed method improves performance on a range of natural language processing tasks. |
On Controlling Fallback Responses for Grounded Dialogue Generation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge grounded dialogue frameworks assume that the user intention is always answerable. |
| Approach: | They propose a framework that automatically generates a control token with the generator to bias the succeeding response towards informativeness for answerable contexts and fallback for unanswerable context. |
| Outcome: | The proposed framework incorporates fallback responses to respond to unanswerable contexts in an informative manner while retaining informativeness for answerable context. |
Query-based Instance Discrimination Network for Relational Triple Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to extract relational triples from open domain texts suffer from error propagation, relation redundancy and lack of high-level connections. |
| Approach: | They propose a query-based approach to construct instance-level representations for relational triples . they use query embeddings and token embeddables to extract all types of triples in one step . |
| Outcome: | The proposed method achieves state-of-the-art on five widely used benchmarks. |
EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. |
| Approach: | They propose a synthetic data generation framework that leverages models’ established English-to-x (en2x) capabilities by extending English parallel corpora into omnidirectional datasets and developing an English-referenced quality evaluation proxy. |
| Outcome: | The proposed framework achieves significant improvement across 72 x2x directions while generalizing to enhance en2x performance. |
LongSafety: Evaluating Long-Context Safety of Large Language Models (2025.acl-long)
Copied to clipboard
Yida Lu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Cunxiang Wang, Xiaotao Gu, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating long sequences. |
| Approach: | They propose a benchmark to evaluate LLM safety in open-ended long-context tasks . they find that relevant context and extended input sequences can exacerbate safety risks . |
| Outcome: | The proposed benchmark identifies significant safety vulnerabilities in 16 LLMs . strong safety performance in short-context scenarios does not correlate with safety in long-contact tasks . |
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to role-playing language models rely on prompt engineering or supervised fine-tuning to emulate character behaviors but neglect the underlying cognitive mechanisms driving these behaviors. |
| Approach: | They propose a novel RPLA adopting a cognize-then-respond reasoning paradigm that leverages dual cognition for more contextually grounded and psychologically coherent responses. |
| Outcome: | The proposed RPLA outperforms baselines and generalizes effectively across diverse role-playing tasks. |
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows (2026.findings-acl)
Copied to clipboard
Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng
| Challenge: | FinWorkBench evaluates real-world enterprise-grade finance and accounting workflows . a human evaluation of GPT 5.1 Pro passes only 38.4% of workflows, a study finds . |
| Approach: | They propose a workflow construction process that combines LLM-assisted mining and expert annotation to build 172 composite workflows. |
| Outcome: | The proposed process combines expert annotation with LLM-assisted mining of workflows from authentic enterprise environments. |
JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning (2024.acl-demos)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) face significant memory constraints when fine-tuning large prompt sequences. |
| Approach: | They propose a framework for PEFT-compatible fine-tuning of large language models, leveraging distributed training. |
| Outcome: | The proposed framework improves performance 12x compared to Hugging Face/DeepSpeed implementation with four GPUs while consuming less than half the VRAM per GPU. |
API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for quantifying uncertainty in large language models with black-box API access are limited due to the complex data distributions and inner model mechanism. |
| Approach: | They propose a conformal prediction method that minimizes the size of prediction sets and ensures a statistical guarantee of the user-defined coverage. |
| Outcome: | The proposed method outperforms existing methods on close-ended and open-ended questions. |
Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective (2025.coling-main)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) are not effective in solving real-world healthcare tasks, but they are able to provide demographic information and provide biased health predictions. |
| Approach: | They evaluate state-of-the-art LLMs with three prevalent learning frameworks across six diverse healthcare tasks and find significant challenges in applying LLM to real-world healthcare tasks. |
| Outcome: | The proposed models perform poorly in real-world healthcare tasks and are inconsistent with existing learning frameworks. |
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)
Copied to clipboard
Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang
| Challenge: | Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level. |
| Approach: | They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context. |
| Outcome: | The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set. |
Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach (2021.acl-long)
Copied to clipboard
| Challenge: | Existing efforts to enhance the performance of session-based cyberbullying detection have overlooked unintended social biases in existing datasets. |
| Approach: | They propose a model-agnostic debiasing strategy that leverages a reinforcement learning technique to mitigate unintended biases in existing datasets. |
| Outcome: | The proposed approach can mitigate unintended biases without impairing the detection performance. |
Explainable Recommendation with Personalized Review Retrieval and Aspect Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Recent years have witnessed a growing interest in the development of explainable recommendation models. |
| Approach: | They propose a model that combines prediction and generation tasks to produce more persuasive explanations by obtaining additional information from the training sets. |
| Outcome: | The proposed model outperforms state-of-the-art models on three datasets and shows that it is more persuasive than previous models. |
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Automatic Speech Recognition (ASR) have been fueled by massive speech corpora, but extending coverage to diverse languages with limited resources remains a formidable challenge. |
| Approach: | They propose a pipeline that converts large-scale text corpora into synthetic speech using off-the-shelf text-to-speech (TTS) models. |
| Outcome: | The proposed pipeline generates 500,000 hours of synthetic speech in ten languages and achieves transcription error reductions of over 30%. |
MDACE: MIMIC Documents Annotated with Code Evidence (2023.acl-long)
Copied to clipboard
Hua Cheng, Rana Jafari, April Russell, Russell Klopfer, Edmond Lu, Benjamin Striner, Matthew Gormley
| Challenge: | Computer-Assisted Coding (CAC) systems are required to provide supporting textual evidence to justify billing codes. |
| Approach: | They propose a dataset for evidence/rationale extraction on an extreme multi-label classification task over long medical documents. |
| Outcome: | The proposed dataset can be used to evaluate evidence extraction methods for CAC systems, as well as the accuracy and interpretability of deep learning models for multi-label classification. |
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)
Copied to clipboard
Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu
| Challenge: | Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs. |
| Approach: | They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets. |
| Outcome: | Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks. |
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)
Copied to clipboard
Jialun Cao, Yaojie Lu, Meiziniu Li, Haoyang Ma, Haokun Li, Mengda He, Cheng Wen, Le Sun, Hongyu Zhang, Shengchao Qin, Shing-Chi Cheung, Cong Tian
| Challenge: | Recent studies in formal mathematical reasoning have shown an unstoppable growth trend. |
| Approach: | They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs. |
| Outcome: | The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps. |
When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models respond even when prompts omit critical details or include misleading information, leading to hallucinations or reinforced misconceptions. |
| Approach: | They propose an interactive benchmark that converts standard QA pairs into multi-turn interactions with explicit checkpoints. |
| Outcome: | The proposed benchmark improves accuracy, rubric adherence, and interaction efficiency with strong generalization to unseen domains. |
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries. |
| Approach: | They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios. |
| Outcome: | The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities. |
Large Language Models for Data Annotation and Synthesis: A Survey (2024.emnlp-main)
Copied to clipboard
Zhen Tan, Dawei Li, Song Wang, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, Mansooreh Karami, Jundong Li, Lu Cheng, Huan Liu
| Challenge: | Existing surveys focus on LLMs' specific utility for data annotation and synthesis. |
| Approach: | They propose to use large language models to generate annotations from raw data . they also propose to review learning strategies for models utilizing LLM-generated annotations . |
| Outcome: | The proposed models can be used to improve the efficacy of machine learning models by generating and labeling raw data with relevant information. |
Exploring Task Difficulty for Few-Shot Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models do not distinguish hard tasks from easy ones in the learning process. |
| Approach: | They propose a novel approach that exploits relation label information to learn better representations by focusing on hard tasks. |
| Outcome: | Experiments on two standard datasets show the proposed approach performs better than previous methods. |
Robust Neural Machine Translation with Doubly Adversarial Inputs (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) models suffer from noisy perturbations in the input . a gradient-based method to craft adversarial examples informed by the translation loss is proposed . |
| Approach: | They propose an approach to improve the robustness of NMT models by attacking the translation model with adversarial source examples and defending the model with a target input. |
| Outcome: | The proposed approach improves translation performance and robustness on clean inputs and higher on noisy data. |
Capturing Latent Modal Association For Multimodal Entity Alignment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for multimodal entity alignment overlook the quality of input modality embeddings during modality interaction, amplifying noise propagation while suppressing discriminative feature representations. |
| Approach: | They propose a model for capturing latent modal association for multimodal entity alignment using a self-attention mechanism to enhance salient information while attenuating noise within individual modality embeddings. |
| Outcome: | The proposed model achieves an absolute 3.1% higher Hits@1 score than the sota method. |
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment (2022.emnlp-main)
Copied to clipboard
| Challenge: | ALCQA addresses the semantic and structural gap between natural language and action sequences . a priori, the semantics of the question and action are not well understood . |
| Approach: | They propose an alignment-enhanced complex question answering framework which aligns questions and actions into sequences. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on a CQA and WQSP dataset. |
QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for reducing LLM hallucinations rely on model-internal signals . Existing approaches rely only on model internal signals, resulting in unreliability . |
| Approach: | They propose a method that shifts from subjective confidence to objective statistics . they leverage Infini-gram for millisecond-latency queries over 4 trillion tokens . |
| Outcome: | The proposed method reduces hallucinations in large language models by reducing uncertainty in the model. |
Scaling Laws for Fact Memorization of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Fact knowledge memorization is crucial for Large Language Models (LLMs) to generate factual and reliable responses. |
| Approach: | They analyze scaling laws for LLM’s fact knowledge and LLMs’ behaviors of memorizing different types of facts. |
| Outcome: | The proposed model can generalize on unseen facts and its scaling law is similar to general pre-training. |
Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation (2026.acl-demo)
Copied to clipboard
| Challenge: | Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices. |
| Approach: | They present a tool that generates QEMU-based virtual devices directly from Linux driver source code. |
| Outcome: | The proposed tool generates QEMU-based virtual devices directly from Linux driver source code. |
ENT-DESC: Entity Description Generation by Exploring Knowledge Graph (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for knowledge-to-text generation use RDF triples or key-value pairs to generate a natural language description. |
| Approach: | They propose a large-scale dataset to facilitate the study of KG-to-text . they propose MGCN model architecture that incorporates aggregation methods to extract the rich graph information. |
| Outcome: | The proposed model can represent the original graph information more comprehensively and integrates multiple aggregation methods to extract the rich graph information. |
APE: Argument Pair Extraction from Peer Review and Rebuttal via Multi-task Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Argument mining is an important research field that attracts growing attention in recent years. |
| Approach: | They propose a new task to extract argument pairs from peer review and rebuttal . they use an open review platform to analyze the contents, structure and connections . |
| Outcome: | The proposed task is based on a dataset of 4,764 fully annotated review-rebuttal passage pairs . it is able to detect argumentative propositions and extract argument pairs from the corpus . |
Generative Prompt Tuning for Relation Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing prompt tuning methods for RC are limited by label spaces and rigid prompt restrictions. |
| Approach: | They propose a generative prompt tuning method to reformulate relation classification as an infilling problem by adding cloze-style phrases to masked language modeling problems. |
| Outcome: | The proposed method exploits rich semantics of entity and relation types and can predict label verbalizations with varying lengths at multiple predicted positions. |
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)
Copied to clipboard
Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains. |
| Approach: | They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries. |
| Outcome: | The proposed system outperforms baselines in the open domain task-solving benchmark. |
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning (2026.findings-acl)
Copied to clipboard
Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang, Fu Li
| Challenge: | Generative engines (GEs) are replacing ranked links with citation-grounded answers . current methods are unable to accumulate or transfer effective strategies across tasks and engines . |
| Approach: | They propose a multi-agent framework where planning, editing, and fidelity-aware evaluation serve as the execution layer. |
| Outcome: | The proposed framework outperforms heuristic baselines in visibility and citation fidelity on three mainstream engines. |
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model (2024.emnlp-main)
Copied to clipboard
Wenqi Zhang, Zhenglin Cheng, Yuanyu He, Mengna Wang, Yongliang Shen, Zeqi Tan, Guiyang Hou, Mingqian He, Yanna Ma, Weiming Lu, Yueting Zhuang
| Challenge: | Using large language models, large multimodal models struggle with basic tasks like reading time from a clock and planning a route using a road map. |
| Approach: | They propose a multimodal self-instruct that synthesizes massive abstract images and visual reasoning instructions. |
| Outcome: | The proposed model synthesizes 11,193 abstract images and reasoning instructions across eight visual scenarios. |