Papers by Yangqiu Song
CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | HKUST-KnowComp proposes a framework for commonsense reasoning that can be used to conceptualize commonsence knowledge bases at scale. |
| Approach: | They propose a framework that integrates event conceptualization and instantiation to conceptualize commonsense knowledge bases at scale. |
| Outcome: | The proposed framework achieves state-of-the-art on two conceptualization tasks and the acquired abstract commonsense knowledge significantly improves commonsence inference modeling. |
MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in LLMs have demonstrated superior performance in a variety of reasoning tasks (Liu et al., 2023b; Chan e t al, 2024; Qin eetal., 2023) However, to truly achieve conscious processing, the integration of System II reasoning ability is essential. |
| Approach: | They propose a three-step process for reasoning with distributional changes, termed as a metaphysical resoning, and propose 'MARS' task to assess LLMs' reasoning abilities. |
| Outcome: | The proposed task is based on a three-step discriminative process and is compared with a standard model with 20 LLMs of varying sizes and methods. |
ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases (2024.eacl-long)
Copied to clipboard
| Challenge: | Reasoning over Commonsense Knowledge Bases (CSKBs) is a way to acquire new commonsense knowledge based on reference knowledge in original CSKB and external prior knowledge. |
| Approach: | They propose a plugin to provide and check explicit relational constraints over prompting techniques. |
| Outcome: | The proposed method improves on existing prompting techniques and CSKB reasoning. |
Multilingual and Multi-Aspect Hate Speech Analysis (D19-1)
Copied to clipboard
| Challenge: | Current research on hate speech analysis is oriented towards monolingual and single classification tasks. |
| Approach: | They propose to use a multilingual multi-aspect hate speech analysis dataset to test current methods . they evaluate the dataset in various classification settings and discuss how to leverage annotations . |
| Outcome: | The proposed dataset can be used to improve hate speech detection and classification in general. |
arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Literature review tables are essential for summarizing and comparing collections of scientific papers. |
| Approach: | They propose to generate a database of literature review tables from a pool of papers and to model retrieval noise via semantically related but out-of-scope distractor papers verified by human annotators. |
| Outcome: | The proposed method improves over strong baselines while the absolute scores remain modest, underscoring the task’s difficulty. |
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs (2024.acl-long)
Copied to clipboard
| Challenge: | Currently, language models struggle to generate commonsense inferences for complex tasks due to data scarcity and the difficulty of reasoning over multiple pieces of information. |
| Approach: | They propose a dataset to generate commonsense inferences from commonsensible data . they use a commonsence knowledge graph to extract and form questions from existing commonseense knowledge graphs. |
| Outcome: | The proposed dataset improves the ability of language models to reason about complex events without expensive human annotations. |
Exophoric Pronoun Resolution in Dialogues with Topic Regularization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on pronoun coreference resolution focus on anaphora and cataphores . exophoric pronounos are common in daily communications, but can be disambiguated by general topics of the dialogue. |
| Approach: | They propose to leverage local context and global topics of dialogues to solve out-of-text PCR problem by adding topic regularization. |
| Outcome: | Extensive experiments show that topic regularization can be used to solve the out-of-text PCR problem. |
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing commonsense reasoning datasets target different knowledge types, modalities, and formats, but how to help machines acquire and infer over commonsensical knowledge is still unclear. |
| Approach: | They propose a commonsense reasoning benchmark to motivate commonsensing progress from two perspectives: (1) Evaluating whether models can distinguish knowledge quality by predicting if the knowledge is enough to answer the question or not. |
| Outcome: | The proposed model outperforms existing models in evaluating their generalization capabilities across tasks while demonstrating that distinguishing knowledge quality remains challenging for current models. |
Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering (2024.emnlp-main)
Copied to clipboard
Yao Xu, Shizhu He, Jiabei Chen, Zihao Wang, Yangqiu Song, Hanghang Tong, Guang Liu, Jun Zhao, Kang Liu
| Challenge: | Existing methods to integrate LLMs with Knowledge Graphs (KGs) however, these methods are often incomplete to cover all the knowledge required to answer questions. |
| Approach: | They propose to integrate LLMs with Knowledge Graphs (KGs) to address insufficient knowledge and hallucination issues in Large Language Models. |
| Outcome: | The proposed method outperforms existing methods on two datasets. |
ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been adopted to process textual task description and accomplish procedural planning in embodied AI tasks because of their powerful reasoning ability. |
| Approach: | They propose to evaluate the planning ability of large language models and multi-modal counterfactual vision language models (VLMs) using a multi-factual household activity simulator and a chatGPT task description to evaluate their reasoning ability. |
| Outcome: | The proposed benchmark evaluates the planning ability of multi-modal and counterfactual vision language models on a household activity simulator and a chatGPT task description. |
Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence (2023.findings-acl)
Copied to clipboard
| Challenge: | Sentence-level representations are beneficial for various natural language processing tasks. |
| Approach: | They propose a generative embedding inversion attack that reconstructs input sequences based only on their sentence embeddeds. |
| Outcome: | The proposed model outperforms previous embedding inversion attacks in classification metrics and generates coherent and contextually similar sentences as original inputs. |
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding (2023.emnlp-main)
Copied to clipboard
Cheng Jiayang, Lin Qiu, Tsz Chan, Tianqing Fang, Weiqi Wang, Chunkit Chan, Dongyu Ru, Qipeng Guo, Hongming Zhang, Yangqiu Song, Yue Zhang, Zheng Zhang
| Challenge: | Analogy-making between narratives is crucial for human reasoning . despite its importance, there has been limited research on story analogies . |
| Approach: | They construct a large-scale story-level analogy corpus with 24K story pairs . they find that the tasks are incredibly difficult for large language models such as ChatGPT . |
| Outcome: | The proposed corpus contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory. |
Defense Against Prompt Injection Attack by Leveraging Attack Techniques (2025.acl-long)
Copied to clipboard
| Challenge: | Recent attacks leverage LLMs’ instruction-following abilities and their inabilities to distinguish instructions injected in the data content. |
| Approach: | They invert the intention of prompt injection methods to develop novel defense methods based on previous training-free attack methods by repeating the attack process with the original input instruction rather than the injected instruction. |
| Outcome: | The proposed methods outperform existing defense approaches, achieving state-of-the-art results. |
TopicAttack: An Indirect Prompt Injection Attack via Topic Transition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent attacks have demonstrated potential, but their abrupt instruction injection often undermines their effectiveness. |
| Approach: | They propose a method that prompts the LLM to generate a fabricated conversational transition prompt that gradually shifts the topic toward the injected instruction. |
| Outcome: | The proposed method achieves state-of-the-art performance with an attack success rate (ASR) over 90% in most cases, even when various defense methods are applied. |
Multiplex Word Embeddings for Selectional Preference Acquisition (D19-1)
Copied to clipboard
| Challenge: | Existing word embeddings are limited in their ability to represent fixed vectors . instead, they incorporate relational dependencies of different words into their embeddables - a limitation that is addressed by a multiplex model . |
| Approach: | They propose a word embedding model which incorporates relational dependencies of different words into their embeddables. |
| Outcome: | The proposed model can be easily extended according to various relations among words. |
You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas (2022.naacl-main)
Copied to clipboard
| Challenge: | Social chatbots evolve rapidly with large pretrained language models. |
| Approach: | They propose effective defense objectives to protect persona leakage from hidden states by a simple neural network. |
| Outcome: | The proposed defense objectives reduce the attack accuracy from 37.6% to 0.5% while preserving language models’ powerful generation ability. |
Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision (P19-1)
Copied to clipboard
| Challenge: | Lack of labeled training data is a major bottleneck for aspect and opinion term extraction . et al., 2004: aspect and opinions are of particular importance for opinion mining . |
| Approach: | They propose to automatically mine extraction rules from existing training examples based on dependency parsing results . they then apply the mined rules to label auxiliary data to train a neural model . |
| Outcome: | The proposed algorithm can learn from human annotated data and human annnotated auxiliary data. |
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)
Copied to clipboard
Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song
| Challenge: | Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning. |
| Approach: | They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized. |
| Outcome: | The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized . |
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song
| Challenge: | Current mitigation strategies fail to preserve contextual reasoning capabilities in risky scenarios, leading to systemic risks for legal compliance. |
| Approach: | They propose to use reinforcement learning with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms. |
| Outcome: | The proposed model outperforms Qwen2.5-7B-Instruct model in safety and privacy benchmarks and achieves +8.58% accuracy improvement. |
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction (2026.findings-acl)
Copied to clipboard
Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Xiaoling Bai, Chi Fei, Li Yabo, Haozhe Ma, Yangqiu Song, Bryan Hooi
| Challenge: | Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions. |
| Approach: | They propose a prompt injection defense method that suppresses the model's instruction-following tendencies rather than suppressing them. |
| Outcome: | The proposed method outperforms prompt-engineering-based approaches and fine-tuning methods and reduces the ASR to nearly 0% in some scenarios. |
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has shown that data collection is neglected by ignoring the quality of data. |
| Approach: | They propose to use latent semantics to evaluate selection bias in hate speech . they compare latent Dirichlet Allocation (LDA) to eleven hate speech corpora . |
| Outcome: | The proposed method could be revisable before focusing on classification performance. |
Can Indirect Prompt Injection Attacks Be Detected and Removed? (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have developed various detection mechanisms to protect against prompt injection attacks. |
| Approach: | They investigate the feasibility of detecting and removing indirect prompt injection attacks . they use two methods to evaluate their performance and train detection models . |
| Outcome: | The proposed method is based on a benchmark dataset and is available on github . it evaluates the performance of existing models and open-source detection models . |
LATENTLOGIC: Learning Logic Rules in Latent Space over Knowledge Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for learning logic rules for knowledge graph reasoning face limitations such as searching in vast search space and inefficient optimization. |
| Approach: | They propose a framework to efficiently mine logic rules by controllable generation in the latent space by a pre-trained VAE and a discriminator. |
| Outcome: | The proposed framework efficiently mines logic rules by controllable generation in the latent space. |
A Survey of RAG-Reasoning Systems in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu
| Challenge: | a survey of RAG-based reasoning-based approaches shows that it is not effective for multi-step inferences. |
| Approach: | They map how advanced reasoning optimizes each stage of RAG . they show how retrieved knowledge supply missing premises and expand context for complex inference . |
| Outcome: | The proposed frameworks achieve state-of-the-art across knowledge-intensive benchmarks. |
PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing approaches to utilizing explicit knowledge graphs (KGs) are limited by the number of nodes in the subgraph. |
| Approach: | They propose a grounding-pruning-reasoning pipeline to prune noisy nodes in subgraphs to improve the efficiency of graph reasoning with KG. |
| Outcome: | The proposed method reduces computation cost and memory usage while obtaining decent representation of pruned subgraphs. |
Weakly Supervised Text Classification using Supervision Signals from a Language Model (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing weakly supervised text classification methods require a large number of annotated data and human annotations are expensive. |
| Approach: | They propose to query a masked language model with cloze style prompts to obtain supervision signals. |
| Outcome: | The proposed method outperforms baseline methods on three datasets by 2%, 4%, and 3%. |
Relation Discovery with Out-of-Relation Knowledge Base as Supervision (N19-1)
Copied to clipboard
| Challenge: | Existing methods to extract relations from text corpus without annotated data are violated by up to 31%. |
| Approach: | They propose to use out-of-relation knowledge bases to supervise the discovery of unseen relations where relations to discover from the text corpus and those in knowledge bases are not overlapped. |
| Outcome: | The proposed method improves the state-of-the-art relation discovery performance by a large margin. |
Joint Coreference Resolution and Character Linking for Multiparty Conversation (2021.eacl-main)
Copied to clipboard
| Challenge: | Character linking is the task of linking mentioned people in conversations to the real world . human use of pronouns or normal entities makes it difficult to link mentioned people to real people . a critical step towards understanding conversations is grounding mentioned people - a goal of the natural language processing community . |
| Approach: | They propose to integrate richer context from the coreference relations among different mentions to help the linking task. |
| Outcome: | The proposed model outperforms all previous models on both tasks. |
QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to QA fine-tune language models on QA pairs constructed from CommonSense Knowledge Bases (CSKBs) however, current QA synthesis protocols introduce noise from the CSKB and generate ungrammatical questions and false negative options, which impede the model’s ability to generalize. |
| Approach: | They propose a framework to analyze the training dynamics of each QA pair at both the question level and option level, discarding machine-detectable artifacts and mislabeled or false-negative options. |
| Outcome: | The proposed framework outperforms baseline approaches while using only 33% of the synthetic data. |
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key? (2024.acl-long)
Copied to clipboard
| Challenge: | Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLM. |
| Approach: | They propose a group discussion framework to enrich the set of discussion mechanisms. |
| Outcome: | The proposed framework performs better on a wide range of reasoning tasks and backbone LLMs. |
Exploring Discourse Structures for Argument Impact Classification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that discourse structures influence the persuasiveness of arguments. |
| Approach: | They propose to fuse sentence-level structural discourse information with contextualized features derived from large-scale language models to investigate how discourse relations influence argument impact. |
| Outcome: | The proposed model improves its backbone RoBERTa around 1.67%, compared with other models, but side effects are brought by other models. |
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020.acl-main)
Copied to clipboard
| Challenge: | a new task is developed to categorize essential commonsense knowledge for the Winograd Schema Challenge . a previous work focused on the classification of commonsensical knowledge by pre-trained models . |
| Approach: | They propose a task that categorizes essential commonsense knowledge for the Winograd Schema Challenge . they leverage the collected reasons to identify plausible reasons from wrong ones . |
| Outcome: | The proposed task aims to shed light on commonsense knowledge needed for better reasoning . it is based on the collected reasons and a new task called WinoWhy . |
Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for answering complex queries on knowledge graphs lack a local and global scoring function. |
| Approach: | They propose a convolution-based algorithm for linear time computation and a block diagonal kernel to enforce the trade-off between local and global embeddings. |
| Outcome: | The proposed model outperforms existing methods on standard datasets, evaluation sets with combinatorially complex queries, and hierarchical knowledge graphs. |
An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work attempts to explicitly incorporate human-defined linguistic priors into fine-tuning tasks. |
| Approach: | They replace parsed graphs or trees with trivial ones to investigate linguistic priors . they propose to use trivial graphs as baselines to design advanced knowledge fusion methods . |
| Outcome: | The use of trivial graphs improves performance in fully-supervised and few-shot settings. |
KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies indicate that language models generate non-factual information that is not supported by evidence with a high level of confidence. |
| Approach: | They propose a knowledge-constrained decoding method that guides a frozen LLM to generate text aligned with the reference knowledge at each decoding step. |
| Outcome: | The proposed method reduces the risk of misinformation generated by LLMs by reducing training costs and catastrophic forgetting for multi-tasking models. |
AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph (2024.findings-naacl)
Copied to clipboard
Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi, Xin Liu, Yangqiu Song
| Challenge: | Existing language models only touch nouns or verbs within simplified events or specific domains. |
| Approach: | They propose an entailment graph that collects abstract knowledge for 3 components of diverse events to comprehensively evaluate the abstraction ability of language models. |
| Outcome: | The proposed benchmark improves LLMs across two previous abstraction tasks. |
NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding (2024.findings-emnlp)
Copied to clipboard
Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song
| Challenge: | Theory of mind evaluations currently focus on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations. |
| Approach: | They propose a benchmark to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states. |
| Outcome: | The proposed benchmark builds upon the Belief-Desire-Intention theory and conducts the necessary empirical experiments to evaluate large language models. |
A Chinese Corpus for Fine-grained Entity Typing (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing datasets for fine-grained entity typing are limited to English . a corpus of 4,800 mentions is manually labeled with free-form entity types . |
| Approach: | They propose a Chinese fine-grained entity typing task that uses crowdsourcing . they categorize each mention into 10 general types and use a large tag set to predict open set of types . |
| Outcome: | The proposed dataset contains 4,800 mentions manually labeled in Chinese . it also categorizes all the fine-grained types into 10 general types . |
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education? (2025.acl-short)
Copied to clipboard
| Challenge: | Existing knowledge discrepancies between textbooks and large language models can undermine RAG systems' performance. |
| Approach: | They propose to use a dataset to test RAG system robustness against knowledge discrepancies. |
| Outcome: | The proposed dataset shows that RAG systems suffer performance degradation when faced with knowledge discrepancies. |
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning (2025.emnlp-main)
Copied to clipboard
Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning. |
| Approach: | They analyze the comparative dynamics of inductive (System 1) versus abductive/deductive (system 2) inference in large language models by using a controlled analogical reasoning environment and a MCQ/free-text task format. |
| Outcome: | The proposed methods can significantly scale LLM reasoning. |
CoCoLM: Complex Commonsense Enhanced Language Model with Discourse Relations (2022.findings-acl)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models have demonstrated strong knowledge representation ability, but struggle with complex commonsense knowledge that involves multiple eventualities. |
| Approach: | They propose to help pre-trained language models better incorporate complex commonsense knowledge that involves multiple eventualities. |
| Outcome: | The proposed model can learn to use the memorized knowledge for different tasks and achieve outstanding performance on many downstream natural language processing (NLP) tasks. |
InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling (2026.acl-long)
Copied to clipboard
Haochen Shi, Tianshi Zheng, Weiqi Wang, Baixuan Xu, Chunyang Li, Chunkit Chan, Tao Fan, Yangqiu Song
| Challenge: | Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs. |
| Approach: | They propose a flexible and scalable multi-dimensional routing framework that models the capability and knowledge of models. |
| Outcome: | The proposed framework can be used to generalize and identify top-performing models for group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench. |
Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to condensing textual information into concise and structured tables are limited in their applicability in broader contexts. |
| Approach: | They propose a benchmark dataset for generating summary tables of competitions based on real-time commentary texts that incorporates large-scale textual information into concise and structured tables. |
| Outcome: | The proposed method exhibits strong generalization abilities, surpassing previous approaches on several other text-to-table datasets. |
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluations on the population task are either not accurate (automatic evaluation with randomly sampled negative examples) or of small scale (human annotation). |
| Approach: | They propose a reasoning over commonsense knowledge bases (CSKBs) that are free-text and have a human annotation set to probe commonsensical reasoning. |
| Outcome: | The proposed model is based on a human-annotated evaluation set and is compared with existing models on the population task. |
DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage. |
| Approach: | They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents. |
| Outcome: | Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget. |
Enhancing Transformers for Generalizable First-Order Logical Entailment (2025.acl-long)
Copied to clipboard
Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li
| Challenge: | Moreover, transformers have demonstrated proficiency in logical reasoning over natural language. |
| Approach: | They propose a logic-aware architecture that improves the performance in generalizable first-order logical entailment by combining distribution shifts and unseen knowledge. |
| Outcome: | The proposed architecture outperforms methods designed specifically for knowledge graph query answering on a dataset with a large dataset. |
XToM: Exploring the Multilingual Theory of Mind for Large Language Models (2026.acl-long)
Copied to clipboard
Chunkit Chan, Yauwai Yim, Hongchuan Zeng, Zhiying Zou, Xinyuan Cheng, Zhifan Sun, Zheye Deng, Kawai Chung, Yuzhuo Ao, Fan Yixiang, Cheng Jiayang, Ercong Nie, Ginny Wong, Helmut Schmid, Hinrich Schuetze, Simon See, Yangqiu Song
| Challenge: | Existing evaluations of ToM in LLMs are limited to English, neglecting the linguistic diversity that shapes human cognition. |
| Approach: | They propose a multilingual benchmark that evaluates ToM across five languages . they find that models excel in multilingual language understanding, but their ToM performance varies across languages. |
| Outcome: | The proposed benchmark evaluates LLMs across five languages and incorporates diverse task scenarios. |
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting (2022.acl-long)
Copied to clipboard
| Challenge: | Word sense disambiguation (WSD) is a problem in the natural language processing community. |
| Approach: | They propose a method to adjust training on imbalanced word sense dataset . they propose to achieve performance gain on standard English all words benchmark . |
| Outcome: | The proposed method achieves performance gain on the standard English all words benchmark. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that LLMs are vulnerable to prompt injection attacks because of their instruction-following abilities and inability to distinguish the instructions in the data content. |
| Approach: | They propose backdoor-powered prompt injection attacks that trick LLMs into deviating from the original input instruction and executing the attackers’ target instruction. |
| Outcome: | The proposed attacks trick the LLMs into deviating from the input instruction and executing the attackers’ target instruction. |
Global Constraints with Prompting for Zero-Shot Event Argument Classification (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing zero-shot trigger extraction models require annotations, which is not practical for open-domain applications. |
| Approach: | They propose to use global constraints with prompting to tackle event argument classification without annotation and task-specific training. |
| Outcome: | The proposed model outperforms the best zero-shot baselines by 12.5% and 10.9% F1 on ACE and ERE with given argument spans and by 4.3% and 3.3% F1 without given argument spas. |
Probing Toxic Content in Large Pre-Trained Language Models (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies on pre-trained language models have shown that they carry harmful biases towards different social groups. |
| Approach: | They propose a method to probe English, French, and Arabic PTLMs and quantify the potentially harmful content they convey with respect to a set of templates. |
| Outcome: | The proposed method analyzes PTLMs to predict masked tokens at the end of sentences to assess their toxicity. |
Query2Particles: Knowledge Graph Reasoning with Particle Embeddings (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to answer complex logical queries on incomplete knowledge graphs with missing edges are needed to solve the problem. |
| Approach: | They propose a query embedding method that encodes queries and entities to the same embeddable space and then selects the answer entities based on similarities . |
| Outcome: | The proposed method can answer complex logical queries on incomplete knowledge graphs with missing edges. |
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)
Copied to clipboard
Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
| Challenge: | Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. |
| Approach: | They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects. |
| Outcome: | The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation. |
SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition (P19-1)
Copied to clipboard
| Challenge: | Selectional Preference (SP) is a common phenomenon in human language and has been shown to be useful in many natural language processing tasks. |
| Approach: | They propose a large-scale evaluation set that provides human ratings for the plausibility of 10,000 SP pairs over five SP relations, covering 2,500 most frequent verbs, nouns, and adjectives in American English. |
| Outcome: | The proposed evaluation sets provide human ratings for plausibility of 10,000 SP pairs over five SP relations covering 2,500 most frequent verbs, nouns, and adjectives in American English. |
COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective (2023.acl-long)
Copied to clipboard
Zhaowei Wang, Quyet V. Do, Hongming Zhang, Jiayao Zhang, Weiqi Wang, Tianqing Fang, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Existing efforts to detect commonsense causation from the causal inference perspective are inadequate to seize commonsensical causations. |
| Approach: | They propose a task to detect commonsense causation between two events in context . they propose 'contextualized commons sense causal reasoning' framework that uses covariates to remove confounding effects . |
| Outcome: | The proposed framework can detect commonsense causality more accurately than baselines. |
SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller (2022.emnlp-main)
Copied to clipboard
| Challenge: | In this paper, we propose a new task of sub-event generation for an unseen process . we use a framework to generate coherent sub-Event sequences for unseened processes . |
| Approach: | They propose a task of sub-event generation for an unseen process to evaluate the understanding of the coherence of subevent actions and objects. |
| Outcome: | The proposed framework can generate coherent sub-event sequences for unseen processes . it can also decode more coherent subevents, demonstrating its effectiveness . |
Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have demonstrated remarkable performance across various reasoning tasks. |
| Approach: | They propose a task that evaluates LLMs’ capability in inferring rules from data fused with noisy examples. |
| Outcome: | The proposed method outperforms other methods with minimal performance degradation under noise and counterfactual task gaps highlight LLMs’ reliance on memorized patterns over genuine abstraction. |
Improving Fine-grained Entity Typing with Entity Linking (D19-1)
Copied to clipboard
| Challenge: | Existing methods for fine-grained entity typing require a large tag set and knowledge of the context. |
| Approach: | They propose a deep neural model that uses context and information from entity linking to improve fine-grained entity typing. |
| Outcome: | The proposed model achieves 5% absolute strict accuracy improvement over the state of the art on two datasets. |
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (2024.acl-long)
Copied to clipboard
Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. |
| Approach: | They propose a framework AbsInstruct to enhance LLMs’ abstract ability through instruction tuning. |
| Outcome: | The proposed framework can enhance LLMs’ abstraction ability with strong generalization performance while maintaining their general instruction-following abilities. |
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction (2026.acl-long)
Copied to clipboard
Hong Ting Tsang, Jiaxin Bai, Haoyu Huang, Qiao Xiao, Tianshi Zheng, Baixuan Xu, Shujie Liu, Yangqiu Song
| Challenge: | Currently, knowledge graphs are decoupled from their downstream application, resulting in suboptimal graph structures. |
| Approach: | They propose a framework to directly optimize KG construction for task performance using Reinforcement Learning (RL). |
| Outcome: | The proposed framework improves performance across multiple QA benchmarks and consistently achieves significant performance gains over task-agnostic baseline graphs. |
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to commonsense reasoning include fine-tuning large pre-trained language models or injecting the entire knowledge base for CKGC. |
| Approach: | They propose to learn commonsense knowledge representation by using a multi-alternative contrastive learning framework on COmmonsense Knowledge graphs. |
| Outcome: | Extensive experiments show that the proposed framework is effective in commonsense reasoning tasks. |
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)
Copied to clipboard
Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song
| Challenge: | a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks. |
| Approach: | They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains . |
| Outcome: | a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively . |
Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that the choice of space for knowledge graph (KG) embeddings has significant effects on the performance of KG completion tasks. |
| Approach: | They propose to use the Fourier transform to convert between real and complex hyperbolic space to capture hierarchical patterns. |
| Outcome: | The proposed models outperform the baseline models for knowledge graph (KG) embeddings. |
Extending Complex Logical Queries on Uncertain Knowledge Graphs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies on logical queries on knowledge graphs overlook the incompleteness of KGs. |
| Approach: | They propose an ML-based approach to answer soft queries on uncertain knowledge . they propose to use forward inference and backward calibration to avoid catastrophic errors . |
| Outcome: | The proposed method ensures there are no catastrophic cascading errors while maintaining the same complexity as state-of-the-art inference algorithms for first-order queries. |
ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods face limited knowledge coverage in existing knowledge bases, infeasibility of annotating labels for an overabundance of commonsense knowledge, and strict knowledge formats. |
| Approach: | They propose a framework that integrates conceptualization and instantiation into the KE pipeline for LLMs to enhance their commonsense reasoning capabilities. |
| Outcome: | The proposed framework diagnoses implausible commonsense knowledge within an LLM and augments the source knowledge to be edited with conceptualization for stronger generalizability. |
ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on LLMs' factual knowledge are unreliable since the questions can vary not only in entity frequency but also in difficulty themselves. |
| Approach: | They propose a benchmark to study the role of knowledge frequency in the performance of large language models (LLMs) it aims to avoid possible semantic shortcuts which is a serious problem of current QA study. |
| Outcome: | The proposed method avoids possible semantic shortcuts and improves on existing proofs. |
EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)
Copied to clipboard
Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song
| Challenge: | Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges . |
| Approach: | They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions. |
| Outcome: | The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset . |
Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Abductive reasoning is the process of making educated guesses to provide explanations for observations. |
| Approach: | They propose a task of complex logical hypothesis generation to generate a complex logique hypothesis that can explain a set of observations. |
| Outcome: | The proposed model generates logical hypotheses closer to the reference hypothesis, but not better on unseen observations. |
EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing frameworks for leveraging background knowledge of narratives are limited. |
| Approach: | They propose a framework to ground free-texts to eventuality-centric KGs for narrative reasoning . their framework is based on a set of probabilistic probabilistic models that are grounded in the real world . |
| Outcome: | The proposed framework outperforms baseline models while providing interpretable evidence. |
Variational Weakly Supervised Sentiment Analysis with Posterior Regularization (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for sentiment analysis require human annotations, but they are scarce. |
| Approach: | They propose a posterior regularization framework to control the posterior distribution of label assignment. |
| Outcome: | The proposed framework improves the variational approach to the weakly supervised sentiment analysis and the performance is more stable with smaller prediction variance. |
What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues (D19-1)
Copied to clipboard
| Challenge: | a core task of natural language understanding is to ground a pronoun to a visual object it refers to . problem arises when people use pronounos to refer to something they can see without prior introduction . a novel visual-aware PCR model is proposed to solve this problem . |
| Approach: | They propose a visual-aware PCR model to ground a pronoun to a visible object . they propose PCR using a large-scale dialogue dataset to investigate this problem . |
| Outcome: | The proposed model can help resolve pronouns in conversational contexts. |
InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing grounding approaches work well for simple queries, but many real-world information needs require synthesizing multiple pieces of evidence. |
| Approach: | They introduce "integrative grounding" to evaluate the ability to ground large language models in external knowledge sources. |
| Outcome: | The proposed approach is robust to redundant evidence, but rationalizes using internal knowledge when information is incomplete. |
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives. |
| Approach: | They propose to detect knowledge conflicts in event temporal reasoning using bias indicators such as event relation prior bias, tense bias, narrative bias, and dependency bias. |
| Outcome: | The proposed method can be applied to Pre-trained Language Models and Large Language Model (LLMs) as additional training data or demonstrations for In- Context Learning. |
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol (2025.emnlp-main)
Copied to clipboard
| Challenge: | Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, but it also brings underexplored safety risks. |
| Approach: | They propose a framework that addresses the missing safety mechanisms in MCP and a taxonomy that captures diverse range of unsafe behaviors observed in MMP scenarios. |
| Outcome: | The proposed framework improves safety performance on state-of-the-art LLMs by capturing unsafe behaviors and analyzing the results. |
Analogous Process Structure Induction for Sub-event Sequence Prediction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on event understanding is focusing on procedural (or horizontal) tasks such as predicting the next event given an observed sequence. |
| Approach: | They propose an Analogous Process Structure Induction framework which leverages analogies among processes and conceptualization of sub-event instances to predict the whole sub- sequence of previously unseen open-domain processes. |
| Outcome: | The proposed framework can predict the whole sub-event sequence of previously unseen open-domain processes. |
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-grained entity typing use weak labels that are automatically generated. |
| Approach: | They propose to obtain training data by using a BERT Masked Language Model (MLM) given a mention in a sentence, they construct an input for the MLM so it predicts context dependent hypernyms of the mention, which can be used as type labels. |
| Outcome: | The proposed model improves performance by using type labels generated from a BERT Masked Language Model given a mention in a sentence. |
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)
Copied to clipboard
Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song
| Challenge: | Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability. |
| Approach: | They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones. |
| Outcome: | The proposed framework shows that it is robust to different prompts and superior to previous methods. |
Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to construct CSKGs with large semantic coverage are expensive and introduce spurious noise. |
| Approach: | They propose a denoising framework that incorporates entity semantic information, global rules, and local structural information from the CSKG. |
| Outcome: | The proposed framework outperforms baseline methods in noise detection tasks on synthetic noisy CSKG benchmarks. |
Incorporating Context and External Knowledge for Pronoun Coreference Resolution (N19-1)
Copied to clipboard
| Challenge: | Existing models for pronoun coreference resolution rely on manual definitions and features to resolve pronounous coreferences. |
| Approach: | They propose a two-layer model for pronoun coreference resolution that leverages both context and external knowledge. |
| Outcome: | The proposed model outperforms state-of-the-art models by a large margin. |
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are catalyzing a paradigm shift in scientific discovery, evolving from task-specific automation tools into increasingly autonomous agents. |
| Approach: | They introduce a foundational three-level taxonomy to delineate their escalating autonomy and evolving responsibilities within the research lifecycle. |
| Outcome: | The proposed frameworks provide a conceptual architecture and strategic foresight to navigate and shape the future of AI-driven scientific discovery. |
Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty? (2025.acl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used in high-stakes domains, but their confidence is inconsistent in out-of-distribution scenarios. |
| Approach: | They define "marker confidence" as the observed accuracy when a model employs an epistemic marker. |
| Outcome: | The proposed model generalizes well within the same distribution, but its confidence is inconsistent in out-of-distribution scenarios. |
Multilingual Word Sense Disambiguation with Unified Sense Representation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing researches on word sense disambiguation focus on English only. |
| Approach: | They propose to build knowledge and supervised based multilingual word sense disambiguation systems on a multilingual lexicon describing the same set of concepts across languages. |
| Outcome: | The proposed model can understand the fine-grained semantics of words under specific contexts. |
PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing PCR systems are not reliable in real applications due to weak semantic meanings of pronouns. |
| Approach: | They propose a benchmark and toolbox that evaluates performance of PCR systems from different perspectives. |
| Outcome: | The proposed benchmark and toolbox evaluates the performance of PCR systems from different perspectives. |
IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce (2024.findings-emnlp)
Copied to clipboard
Wenxuan Ding, Weiqi Wang, Sze Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Junxian He, Yangqiu Song
| Challenge: | Existing approaches that distill intentions from LMs fail to generate meaningful and human-centric intentions applicable in real-world E-commerce contexts. |
| Approach: | They propose a double-task multiple-choice question answering benchmark to evaluate LMs' comprehension of purchase intentions in E-commerce. |
| Outcome: | The proposed benchmark consists of 4,360 carefully curated problems across three difficulty levels, constructed using an automated pipeline to ensure scalability on large E-commerce platforms. |
ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance (2026.acl-long)
Copied to clipboard
Haoran Li, Yulin Chen, Huihao Jing, Wenbin Hu, Tsz Ho Li, Chanhou Lou, Hong Ting Tsang, Sirui Han, Yangqiu Song
| Challenge: | Existing approaches to contextualize safety and privacy assessments assume the availability of complete and clear context, whereas real-world contexts tend to be ambiguous and incomplete. |
| Approach: | They propose a semi-rule-based framework that leverages large language models to ground the input context in the legal domain and explicitly identify both known and unknown factors for legal compliance. |
| Outcome: | The proposed framework can significantly improve existing baselines without training and can identify the ambiguous and missing factors. |
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM safety datasets rely on ad-hoc taxonomies and lack rule-grounded, real-world cases. |
| Approach: | They construct a rule-grounded, real-world case dataset OmniCompliance-100K from a compliance perspective using a powerful web-searching agent. |
| Outcome: | The proposed dataset spans 74 regulations and policies across a wide range of domains including security and privacy regulations, content safety and user data privacy policies, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights. |
Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing privacy studies focus on sub-fields, but they focus on a few sub-domains. |
| Approach: | They propose to use the Health Insurance Portability and Accountability Act of 1996 as an example to develop a checklist that covers social identities, private attributes, and existing privacy regulations. |
| Outcome: | The proposed checklist covers social identities, private attributes, and existing privacy regulations. |
CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot commonsense question answering use incomplete CSKBs . lack of human annotations makes sampled negative examples potentially uninformative and contradictory. |
| Approach: | They propose a framework that abstracts a commonsense knowledge triple to many higher-level instances, which increases the coverage of the CSKB and expands the ground-truth answer space. |
| Outcome: | Experiments show that CAR can generalize to zero-shot commonsense scenarios . lack of human annotations makes sampled negative examples potentially uninformative and contradictory. |
CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning (2024.acl-long)
Copied to clipboard
Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, Yangqiu Song
| Challenge: | Existing approaches to generalize commonsense reasoning lack instantiated knowledge and require pre-built concept taxonomies and annotations. |
| Approach: | They propose a framework that iteratively performs contextualized conceptualization and instantiation over commonsense knowledge bases by instructing large language models to generate both types of knowledge with critic filtering. |
| Outcome: | Empirical results show that distilling CANDLE on student models provides benefits across three downstream tasks. |
Exploring the Potential of ChatGPT on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies have demonstrated ChatGPT's remarkable few-shot, even zero-shot learning abilities when compared to other models. |
| Approach: | They quantitatively evaluate the performance of ChatGPT on inter-sentential relations such as temporal relations, causal relations, and discourse relations. |
| Outcome: | The proposed model performs well on temporal relations, causal relations, and discourse relations. |
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | a taxonomy is a semantic hierarchy of words or concepts organized w.r.t. their hypernymy relationships. |
| Approach: | They propose a framework for hypernymy detection using large textual corpora . they quantify the non-negligible existence of specific sparsity cases . |
| Outcome: | The proposed framework quantifies the non-negligible existence of specific sparsity cases on several benchmark datasets. |
ECON: On the Detection and Resolution of Evidence Conflicts (2024.emnlp-main)
Copied to clipboard
Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang
| Challenge: | Recent studies have shown that AI generated content is more likely to dominate search results, making it difficult to detect when compared to human-produced content. |
| Approach: | They propose a method for generating diverse, validated evidence conflicts to simulate real-world misinformation scenarios. |
| Outcome: | The proposed method enables the detection of conflicting information in real-world scenarios and shows that weaker models struggle with similar answer conflicts while stronger models show robust performance. |
GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing research studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined patterns. |
| Approach: | They propose a framework that leverages the theory of contextual integrity as a bridge to help LLMs understand the complex contexts for judicial assessing privacy violations. |
| Outcome: | The proposed framework bridges the theory of contextual integrity as a bridge, creating numerous synthetic scenarios grounded in relevant privacy statutes (e.g., HIPAA). |
Knowledge-aware Pronoun Coreference Resolution (P19-1)
Copied to clipboard
| Challenge: | Existing models for pronoun coreference resolution only use triplets, the most common format for knowledge graphs. |
| Approach: | They propose a model that leverages different types of knowledge to resolve pronoun coreference with a neural model. |
| Outcome: | The proposed model outperforms state-of-the-art baselines on two datasets from different domains. |
Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)
Copied to clipboard
Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song
| Challenge: | Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions. |
| Approach: | They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions. |
| Outcome: | The proposed model outperforms state-of-the-art methods and shows its utility. |
Multi-step Jailbreaking Privacy Attacks on ChatGPT (2023.findings-emnlp)
Copied to clipboard
| Challenge: | With the rapid evolution of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. |
| Approach: | They propose to integrate ChatGPT and Bing GPT3 into their applications to create a set of LLMs that can be used to generate NLP tasks with appropriate prompts. |
| Outcome: | The proposed models can be zero-shot or few-shot learners to solve specified tasks and can even be zero or few shot learners. |
DIXITWORLD: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay (2026.acl-short)
Copied to clipboard
Yunxiang MO, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song
| Challenge: | Existing evaluations of multimodal abductive reasoning are limited to static, single-agent tasks. |
| Approach: | They propose a multiagent evaluation suite that deconstructs the current evaluations of multimodal abductive reasoning in vision–language models. |
| Outcome: | The evaluation suite is based on two core components: DixitArena and DixitsBench. |
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)
Copied to clipboard
Ki Sen Hung, Xi Yang, Chang Liu, Haoran Li, Kejiang Chen, Changxuan Fan, Tsun On Kwok, Weiming Zhang, Xiaomeng Li, Yangqiu Song
| Challenge: | a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes. |
| Approach: | They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries. |
| Outcome: | a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say . |
DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing works on implicit discourse relation recognition focus on syntax features and lack of connectives. |
| Approach: | They propose a prompt-based path prediction method that integrates the interactive information and intrinsic senses among the hierarchy in IDRR. |
| Outcome: | The proposed method shows significant improvement against competitive baselines. |
On-the-fly Denoising for Data Augmentation in Natural Language Understanding (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to improve data augmentation performance may introduce noisy data that impairs training. |
| Approach: | They propose an on-the-fly denoising technique that learns from soft augmented labels provided by an organic teacher model trained on the cleaner original dataset. |
| Outcome: | The proposed method improves on text classification and question-answering tasks on general augmentation techniques and prevents overfitting on noisy labels. |
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)
Copied to clipboard
Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song
| Challenge: | Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used. |
| Approach: | They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark. |
| Outcome: | The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history. |
FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)
Copied to clipboard
Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin
| Challenge: | Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships. |
| Approach: | They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph. |
| Outcome: | The proposed framework can model e-commerce knowledge and have many potential applications. |
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)
Copied to clipboard
Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song
| Challenge: | generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation. |
| Approach: | They propose a privacy evaluation benchmark to quantify the privacy leakage of language models. |
| Outcome: | The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled. |
CogCompNLP: Your Swiss Army Knife for NLP (L18-1)
Copied to clipboard
Daniel Khashabi, Mark Sammons, Ben Zhou, Tom Redman, Christos Christodoulopoulos, Vivek Srikumar, Nicholas Rizzolo, Lev Ratinov, Guanheng Luo, Quang Do, Chen-Tse Tsai, Subhro Roy, Stephen Mayhew, Zhili Feng, John Wieting, Xiaodong Yu, Yangqiu Song, Shashank Gupta, Shyam Upadhyay, Naveen Arivazhagan, Qiang Ning, Shaoshi Ling, Dan Roth
| Challenge: | a corpus-reader module supports popular corpora, feature extraction and annotation modules for semantic and syntactic tasks. |
| Approach: | They propose a library that provides modules to address different challenges . they provide a corpus-reader module that supports popular corpora in the NLP community . |
| Outcome: | The proposed library simplifies the process of design and development of NLP applications by providing modules to address different challenges. |
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification (N19-1)
Copied to clipboard
| Challenge: | Existing weakly supervised methods for document-level multi-aspect sentiment classification are not easy to obtain. |
| Approach: | They propose a variational approach to weakly supervised document-level multi-aspect sentiment classification using target-opinion word pairs as "supervision" they aim to learn a sentiment polarity classifier by optimizing the lower bound . |
| Outcome: | The proposed method outperforms weakly supervised baselines on TripAdvisor and BeerAdvocate datasets and can be comparable to state-of-the-art supervised methods with hundreds of labels per aspect. |
PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance (2025.acl-long)
Copied to clipboard
Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song
| Challenge: | Recent advances in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. |
| Approach: | They propose a contextual privacy evaluation benchmark that covers the entire relevant social context through private information flows. |
| Outcome: | The proposed benchmarks cover legal compliance, real court cases, privacy policies, and synthetic data. |
Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction (2025.naacl-short)
Copied to clipboard
| Challenge: | Recent research has revealed that Large Language Models (LLMs) often experience issues with hallucinations and unreliable reasoning due to semantic associations and superficial logical chains. |
| Approach: | They propose a concept-reversed Winograd Schema Challenge dataset to evaluate the robustness of Large Language Models (LLMs) they propose Abstraction-of-Thought (AoT) method for recovering adversarial cases to normal cases using conceptual abstraction to improve LLMs’ robustness and consistency in reasoning. |
| Outcome: | The proposed method improves LLMs’ robustness and consistency in reasoning under adversarial and long-tail scenarios. |
Entity Linking within a Social Media Platform: A Case Study on Yelp (D18-1)
Copied to clipboard
| Challenge: | Existing studies on entity linking focus on linking entities to knowledge bases, but on social media platforms, such as Yelp, it can be more practical. |
| Approach: | They propose to link entities within a social media platform with a new entity linking problem. |
| Outcome: | The proposed model can link business mentions to corresponding businesses on a social media platform. |
PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, but it requires out-of-domain generalization ability as the source CSMB for training is of a relatively smaller scale (1M) . |
| Approach: | They propose a semi-supervised learning framework that uses a teacher model to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from. |
| Outcome: | The proposed framework can improve the backbone model KG-BERT (RoBERTa-large) by 3.3 points on the overall performance and especially, 5.3 points on out-of-domain performance. |