Papers with semantic understanding
Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification (2025.acl-short)
Copied to clipboard
| Challenge: | Current intent classification systems face significant challenges due to the vast number of possible intents and significant semantic overlap among similar intent classes. |
| Approach: | They propose a dynamic label refinement method that retrieves relevant examples for a test input and leverages a large language model to dynamically refine intent labels based on semantic understanding. |
| Outcome: | The proposed method resolves confusion between semantically similar intents and generates more interpretable intent labels. |
DEMO: A Statistical Perspective for Efficient Image-Text Matching (2024.naacl-long)
Copied to clipboard
| Challenge: | Image-text matching is a problem that seeks to connect vision and language through semantic understanding. |
| Approach: | They propose a deep unsupervised hashing-based approach for image-text matching . they characterize each image using multiple augmented views, which are considered as samples . |
| Outcome: | The proposed approach achieves superior performance on image-text matching datasets compared with state-of-the-art methods. |
Scaling Properties of Speech Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Speech Language Models (SLMs) aim to learn language from raw audio without textual resources. |
| Approach: | They propose to use scaling properties of neural language models to estimate scale at which SLMs will be trained . they establish a strong correlation between pre-training loss and downstream syntactic and semantic performance . |
| Outcome: | The proposed model will have the English proficiency of text-based Large Language Models. |
Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for commonsense question generation produce shallow questions that can be answered by simple word matching. |
| Approach: | They propose a task of commonsense question generation that aims to yield deep-level questions from the text. |
| Outcome: | The proposed model can yield deep-level and to-the-point questions from the text. |
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders (2024.acl-long)
Copied to clipboard
| Challenge: | Conversational systems often rely on embedding models for intent classification and intent clustering tasks. |
| Approach: | They propose a toolkit that gives a more holistic view of intent embedding models by considering three tasks– (1) intent classification, (2) intent clustering, and (3) a novel triplet task. |
| Outcome: | The proposed model improves on the linguistic dimensions while affecting performance on downstream task metrics. |
Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-trained language models can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. |
| Approach: | They propose a two-stage framework to integrate a linearized knowledge into plan text using a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact. |
| Outcome: | The proposed framework improves the performance of pre-trained language models by using section-aware strategies to encode the linearized knowledge. |
Asking the Right Question: Inferring Advice-Seeking Intentions from Personal Narratives (N19-1)
Copied to clipboard
| Challenge: | To properly infer the intention of the narrator, one needs a certain degree of common sense and social intuition. |
| Approach: | They propose a task that uses common sense to extract pairs of questions that are appropriate candidates for the task. |
| Outcome: | The proposed method exploits commonalities in experiences people share online to extract pairs of semantically plausible advice-seeking questions that are appropriate candidates for the cloze task. |
Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing foundation models for tabular transactional data rely on index-based representations for categorical merchant fields. |
| Approach: | They propose a framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models. |
| Outcome: | The proposed framework improves performance on large transaction datasets. |
Hashing based Efficient Inference for Image-Text Matching (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on image-text matching has focused on exploring interactions between images and sentences to improve performance without considering inference efficiency. |
| Approach: | They propose a hashing-based efficient inference module which can be plugged into existing frameworks to speed up inference step without reducing retrieval performance. |
| Outcome: | The proposed module can be plugged into existing framework to speed up inference step without reducing retrieval performance. |
A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using a zero-shot classification model, we extracted multi-dimensional evaluative features from human expert critiques and used them to evaluate selected VLMs such as Llama, Qwen, or Gemini. |
| Approach: | They constructed a quantitative framework for Chinese painting critique by extracting multi-dimensional evaluative features from human expert critiques using a zero-shot classification model. |
| Outcome: | The framework was constructed by extracting features from human critiques using a zero-shot classification model. |
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding (2026.acl-long)
Copied to clipboard
Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei LI, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang
| Challenge: | Large language models (LLMs) have shown promise on understanding and reasoning over tables, but current approaches remain limited. |
| Approach: | They propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. |
| Outcome: | The proposed framework decomposes table reasoning into three specialized roles: planning, coding, and answering. |
Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on LMs lack systematic studies on their structured reasoning capabilities over the infused knowledge. |
| Approach: | They investigate how LMs of different sizes can store world knowledge of different frequencies in a large-scale KB after training on the abundant world knowledge triplets. |
| Outcome: | The proposed models can store and respond to natural language queries with flexibility and reasoning abilities, but they need to be enhanced to fully realize their potential. |
Revisiting Automatic Evaluation of Extractive Summarization Task: Can We Do Better than ROUGE? (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate text summarization tasks using ROUGE have been criticized for lack of semantic understanding. |
| Approach: | They propose a semantic-aware metric for extractive summarization task that is semantic-based . they use CNN/DailyMail dataset to study the new metric . |
| Outcome: | The proposed metric is semantic-aware and shows higher correlation with human judgement and yields a large number of disagreements with the original ROUGE metric. |
Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection (2025.naacl-long)
Copied to clipboard
Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli, Maximilian Muschalik, Barbara Hammer, Eyke Hüllermeier, Henning Wachsmuth
| Challenge: | Existing prompting techniques for large language models depend on several parameters, such as the task, language model, and context provided. |
| Approach: | They propose an adaptive prompting approach that predicts the optimal prompt composition ad-hoc for a given input. |
| Outcome: | The proposed approach ensures high detection performance and is best in several settings. |
LTRS: Improving Word Sense Disambiguation via Learning to Rank Senses (2025.coling-main)
Copied to clipboard
| Challenge: | Conventional training strategies only consider predefined senses for target words and learn each of them from relatively limited instances, neglecting the influence of similar ones. |
| Approach: | They propose a method to rank senses to improve the task of word Sense Disambiguation (WSD) by ranking an expanded list of sense definitions. |
| Outcome: | The proposed method achieves a SOTA F1 score of 79.6% in Chinese WSD and shows faster convergence than previous methods. |
Accurate and Nuanced Open-QA Evaluation Through Textual Entailment (2024.findings-acl)
Copied to clipboard
| Challenge: | Open-domain question answering (Open-QA) evaluations are criticized for the ambiguity in questions and the lack of semantic understanding in evaluators. |
| Approach: | They propose to examine the entailment relations of answers to identify more informative and more general system answers. |
| Outcome: | The proposed evaluations offer a much closer evaluation to human judgment on NaturalQuestions and TriviaQA while being learning-free. |
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)
Copied to clipboard
| Challenge: | obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data. |
| Approach: | They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models. |
| Outcome: | The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit. |
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)
Copied to clipboard
Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang
| Challenge: | Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information. |
| Approach: | They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format. |
| Outcome: | The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots. |
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval (2024.acl-long)
Copied to clipboard
| Challenge: | Dense retrieval requires discriminative embeddings to represent the semantic relationship between query and document. |
| Approach: | They propose an unsupervised approach that performs unsupervised adaptation of large language models for dense retrieval. |
| Outcome: | The proposed model improves on a variety of dense retrieval benchmarks and is available on github. |
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a lack of comprehensive benchmarks for Routing large language models has hindered the development of routers. |
| Approach: | They propose a router-based benchmark to evaluate Routing large language models . the benchmark includes performance records for 12 popular LLM evaluations . |
| Outcome: | The proposed model-level scaling up phenomenon can surpass the best single model in the pool and many existing strong LLMs. |
On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping (N19-1)
Copied to clipboard
| Challenge: | Sense representations target meaning conflation deficiency but their potential impact has not been investigated in downstream NLP applications. |
| Approach: | They propose to use a reverse dictionary system to address meaning conflation deficiency . they propose to integrate senses into the system to improve semantic understanding . |
| Outcome: | The proposed approach can improve the performance of a downstream NLP application. |
Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for speaker identification in novel dialogues are limited to handling explicit narrative patterns and complex cases. |
| Approach: | They propose a framework which identifies implicit speakers in novels via symbolization, prompt, and classification. |
| Outcome: | The proposed framework outperforms existing methods by 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and outperfies the emerging ChatGPT. |
DASA-Trans-STM: Adaptive Efficient Transformer for Short Text Matching using Data Augmentation and Semantic Awareness (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have shown impressive versatility across various tasks. |
| Approach: | They propose a novel adaptive Transformer for Chinese short text matching using data augmentation and semantic awareness. |
| Outcome: | The proposed model can deal with word ambiguity in Chinese on four available datasets. |
AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting (2025.acl-long)
Copied to clipboard
| Challenge: | Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations. |
| Approach: | They propose a training-free Analogical Replay reasoning framework that uses LLMs to extract historical contexts and generate analogical reasoning examples as contextual inputs. |
| Outcome: | The proposed model outperforms existing training-free methods on four benchmarks. |
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work has used text-based games as a testbed for developing autonomous agents that operate using natural language. |
| Approach: | They propose an inverse dynamics decoder to regularize representation space and encourage exploration to reduce the amount of semantic information available to a learning agent. |
| Outcome: | The proposed model achieves high scores even in the absence of language semantics on Zork I . |
Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated Annotation (2022.naacl-main)
Copied to clipboard
| Challenge: | Conventional exact or approximate termbased retrieval methods lack the ability of semantic understanding of the clinical as well as language context. |
| Approach: | They combine clinical finding detection with supervised query match learning to train a model . findings are used as queries to train the Sentence-BERT model using triplet loss . |
| Outcome: | The proposed method outperforms existing methods on multiple retrieval benchmarks. |
Scented-EAE: Stage-Customized Entity Type Embedding for Event Argument Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for incorporating entities into EAE rely on prompts or NER . weak semantic associations due to missing role-entity correspondence cues . one-sided semantic understanding relying solely on argument role semantics a problem . |
| Approach: | They propose an EAE model with stage-customized entity type embedding to explore the role of entity types. |
| Outcome: | The proposed model achieves state-of-the-art performance on mainstream benchmarks and robustness in low-resource settings. |
Iterative Self-Correction for Text-Driven Person Re-Identification with Large Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Person Re-Identification (ReID) adopt a static "one-pass" paradigm, converting images to text once for retrieval. |
| Approach: | They propose a framework that reformulates ReID as an iterative "Think-and-Refine" process. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in complex occlusion scenarios. |
Retrieval-Augmented Generation with Hierarchical Knowledge (2025.findings-emnlp)
Copied to clipboard
Haoyu Huang, Yongfeng Huang, Yang Junjie, Zhenyu Pan, Yongqiang Chen, Kaili Ma, Hongzhi Chen, James Cheng
| Challenge: | Existing RAG methods do not utilize hierarchical knowledge in human cognition, which limits the capabilities of RAG systems. |
| Approach: | They propose a graph-based approach that utilizes hierarchical knowledge to enhance the semantic understanding and structure capturing capabilities of RAG systems. |
| Outcome: | The proposed approach achieves significant performance improvements over the state-of-the-art methods. |
𝒮2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction (2025.findings-naacl)
Copied to clipboard
| Challenge: | Aspect Sentiment Quad Prediction (ASQP) is an extractive task that focuses on predicting tuples of sentiment-related elements from a given text. |
| Approach: | They propose a stepwise syntax integration tuning framework that integrates syntactic structure knowledge into LLMs through a multi-step tuning process. |
| Outcome: | The proposed framework integrates syntactic structure knowledge into large language models . it decomposes the quadruple generation task into two stages . the proposed framework significantly improves state-of-the-art performance across multiple datasets . |
TimeR4 : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering (2024.emnlp-main)
Copied to clipboard
| Challenge: | Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge in Temporal knowledge graphs (TKTs). |
| Approach: | They propose a Time-aware retrieve-rewrite-retrieve-rerank framework to integrate temporal knowledge from TKGs into Large Language Models (LLMs) to reduce temporal hallucination, they propose rewrite module to rew questions using background knowledge stored in TKG's, then implement a retrieve-rank module to retrieve semantically and temporally relevant facts from Tkgs and rerank them according to temporal constraints. |
| Outcome: | The proposed approach achieves relative gains of 47.8% and 22.5% on two datasets, underscoring its effectiveness in boosting the temporal reasoning abilities of LLMs. |
HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for retrieving dialogue data often face challenges in capturing semantic intent or require extensive labeling and fine-tuning. |
| Approach: | They propose a framework that enhances semantic understanding in conversational data retrieval by optimizing data ingestion. |
| Outcome: | The proposed framework outperforms fine-tuned models in retrieval and intent analysis. |
Evaluating Tokenizers Impact on OOVs Representation with Transformers Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Pre-trained Transformer models have proven their effectiveness in adapting to multiple NLP tasks and domains. |
| Approach: | They evaluated three categories of out-of-vocabulary words using three French domain-specific datasets on the legal, medical, and energetical domains to robustly analyze these categories. |
| Outcome: | The proposed models can create new representations for out-of-vocabulary words by adding external morpho-syntactic context rather than improving the semantic understanding of the words directly. |
H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for tabular reasoning combine textual and symbolic reasoning in a two-stage process to address these limitations. |
| Approach: | They propose an algorithm that integrates symbolic and semantic (textual) approaches in a two-stage process to address these limitations. |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods across three tabular question-answering and fact-verification datasets, underscoring its effectiveness and efficiency. |
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Text-based reinforcement learning is a form of interactive fiction where players manipulate the environment using text and admissible actions in natural language. |
| Approach: | They show that rich semantic understanding leads to efficient training of text-based RL agents . they also show that semantic degeneration occurs when LMs are inappropriately fine-tuned . |
| Outcome: | The results suggest that semantic understanding is not important for the task . they also show that fine-tuning language models can degenerate the agent's performance . |
Semantic-Eval : A Semantic Comprehension Evaluation Framework for Large Language Models Generation without Training (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have emerged as key drivers of progress in the field of natural language processing. |
| Approach: | They propose a framework that assesses LLM-generated text based on semantic understanding. |
| Outcome: | The proposed framework surpasses traditional evaluation metrics and lags behind GPT-4. |
Plan Dynamically, Express Rhetorically: A Debate-Driven Rhetorical Framework for Argumentative Writing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Argumentative essay generation (AEG) is a complex task that requires advanced semantic understanding, logical reasoning, and organized integration of perspectives. |
| Approach: | They propose a debate-driven rhetorical framework for argumentative writing that integrates Bitzer’s rhetorical situation theory to improve logical depth, argumentative diversity, and rhetorical persuasiveness. |
| Outcome: | The proposed framework improves logical depth, argumentative diversity, and rhetorical persuasiveness over existing state-of-the-art models. |
A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems (2021.emnlp-main)
Copied to clipboard
Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya
| Challenge: | Existing methods to improve NLU are laborintensive and expensive. |
| Approach: | They propose a scalable and automatic approach to improving NLU in a large-scale conversational AI system by leveraging implicit user feedback. |
| Outcome: | The proposed framework improves NLU in a large-scale conversational AI system across 10 domains. |
Improving Large Language Models in Event Relation Logical Prediction (2024.acl-long)
Copied to clipboard
| Challenge: | Event relation extraction tasks require rigorous logical reasoning and semantic comprehension, a challenge for narrative understanding and reasoning. |
| Approach: | They propose three approaches to endow LLMs with event relation logic to generate more coherent answers across different scenarios. |
| Outcome: | The proposed approach improves on a set of ERE tasks and provides insights for future work. |
ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Chinese Spelling Check (CSC) aims to identify and correct spelling errors in Chinese texts, where enhanced semantic understanding of a sentence can significantly improve correction accuracy. |
| Approach: | They propose a plug-and-play Alignment-and -Replacement module that enhances existing Chinese CSC models without retraining or fine-tuning. |
| Outcome: | The proposed module improves existing models while reducing retraining and fine-tuning. |
POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex Events (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing language models lag behind human performance in subtle ways in understanding complex situations, e.g., if the Argentine government yields to [IMF] pressure to rescind emergency legislation meant to protect ordinary families like the Brofmans. |
| Approach: | They propose to pre-identify a participant in a complex event and annotate their volitional engagement in causing the situation. |
| Outcome: | The proposed model can be used to infer the collective impact of salient events that make up a complex event, annotate volitional engagement of participants, and ground the outcome in state changes of the participants. |
“A Buster Keaton of Linguistics”: First Automated Approaches for the Extraction of Vossian Antonomasia (D19-1)
Copied to clipboard
| Challenge: | Vossian Antonomasia is a stylistic device which attributes a property to a person by naming another person as a reference point. |
| Approach: | They propose a method for the extraction of Vossian Antonomasias that works completely automatically . they use named entity recognition, distant supervision and a bi-directional LSTM . |
| Outcome: | The proposed method outperforms the only existing semi-automatic method for VA identification by more than 30 percentage points in precision. |
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)
Copied to clipboard
Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie
| Challenge: | Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling. |
| Approach: | They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement. |
| Outcome: | The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks. |
Retrieval-Augmented Generation for Large Language Model based Few-shot Chinese Spell Checking (2025.coling-main)
Copied to clipboard
| Challenge: | Existing LLM-based Chinese spelling check methods rely on fixed prompt samples . existing methods are limited by technical bottlenecks, complex recognition environments, and individual differences . |
| Approach: | They propose a framework called RagID to provide well-chosen prompt samples . they propose to use semantic-based similarity search and iterative discriminator mechanism . |
| Outcome: | The proposed framework can provide well-chosen prompt samples and reduce overcorrection issues in Chinese spelling check tasks. |
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics that reflect the performance of causal event extraction tasks are poorly reflecting the inherent ambiguity of cause and effect boundaries. |
| Approach: | They propose to use a weak-to-strong supervision method to train an evaluation model while still achieving high performance in training an RL model. |
| Outcome: | The proposed method achieves high agreement with human-annotated data while still achieving high performance in training an RL model. |
Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling (2024.lrec-main)
Copied to clipboard
| Challenge: | Topic modelling has found extensive use in automatically detecting significant topics within a corpus of documents, but there are certain drawbacks. |
| Approach: | They propose a framework that prompts large language models to generate topics from a given set of documents and establish evaluation protocols to assess the clustering efficacy of LLMs. |
| Outcome: | The proposed model generates relevant topic titles and adheres to human guidelines to refine and merge topics. |
Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained large language models (LLMs) with world knowledge and semantic understanding are promising for task-oriented dialogue systems. |
| Approach: | a framework that synergizes pre-trained large language models with DRL is proposed . a lightweight action pruning mechanism is employed to eliminate implausible actions . |
| Outcome: | a new framework synergizes pre-trained large language models with DRL to guide decision-making . the proposed framework eliminates semantically implausible or low-potential actions from multi-turn dialogue context . |
DiffCL: Difference-Aware Contrastive Learning for Automatic Answer Grading with Multi-Level Semantic Modeling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to automate answer grading lack semantic understanding and scoring consistency. |
| Approach: | They propose a difference-aware AAG framework that integrates heuristic difference labeling with dual-contrastive learning. |
| Outcome: | The proposed method outperforms cross-entropy-based baselines on SciEntsBank and Beetle datasets. |
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Prior research addresses generating attributions alongside responses in open domains, either per sentence or per paragraph. |
| Approach: | They propose a method to decompose generated answers for attribution using template-based in-context learning. |
| Outcome: | The proposed approach enhances the semantic understanding of abstractive and extractive answers. |
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)
Copied to clipboard
Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability . |
| Approach: | They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR . |
| Outcome: | The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks. |
Adversarial Tokenization (2025.acl-long)
Copied to clipboard
| Challenge: | Current LLM pipelines account for only one possible tokenization for a given string . authors: noncanonical tokenizations can evade LLM safety while still generating meaningful responses. |
| Approach: | They show that LLM pipelines account for only one possible tokenization for a given string . they show that tokenizers retain semantic understanding of other tokenizations . authors propose an exploit that can be exploited to evade safety and alignment restrictions . |
| Outcome: | The proposed exploit exploits a previously unknown vulnerability in subword models. |
Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs (2025.emnlp-main)
Copied to clipboard
Wafa Al Ghallabi, Ritesh Thawkar, Sara Ghaboura, Ketan Pravin More, Omkar Thawakar, Hisham Cholakkal, Salman Khan, Rao Muhammad Anwer
| Challenge: | a benchmark is designed to assess the comprehension of Arabic poetry by large language models in 12 historical eras. |
| Approach: | They propose a benchmark to assess the comprehension of Arabic poetry by large language models in 12 historical eras. |
| Outcome: | The benchmark assesses the comprehension of Arabic poetry by large language models in 12 historical eras. |
Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models (2025.findings-acl)
Copied to clipboard
Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen
| Challenge: | Existing benchmarks focus on linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate numerical capabilities for large language models . they use a dataset to assess number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning. |
| Outcome: | The proposed benchmark evaluates six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning. |
Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Experiments with AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-text retrieval performance to state-of-the-art M2D-CLAP. |
| Approach: | They propose a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding that allows users to express their queries in five different ways. |
| Outcome: | Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP while demonstrating clear advantages in two critical areas. |
Memorization ≠ Understanding: Do Large Language Models Have the Ability of Scenario Cognition? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive performance across NLP tasks. |
| Approach: | They propose a framework to assess LLMs’ scenario cognition . they examine the ability to link semantic scenario elements with their arguments in context . |
| Outcome: | The proposed framework assesses large language models’ scenario cognition . it shows that current models rely on superficial memorization, failing to achieve robust semantic scenario cognition even in simple cases. |
Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for retrieval of information excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks. |
| Approach: | They propose a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. |
| Outcome: | The proposed model outperforms existing models on a BRIGHT benchmark with BM25 retrievers. |
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks. |
| Approach: | They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA . |
| Outcome: | The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications. |
How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future (2025.emnlp-main)
Copied to clipboard
| Challenge: | Entity alignment (EA) is critical for knowledge graph (KG) integration. |
| Approach: | They propose a taxonomy that categorizes methods in three stages: data preparation, feature embedding, and alignment. |
| Outcome: | The proposed taxonomy categorizes methods in three key stages: data preparation, feature embedding, and alignment. |
Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Continued Pre-Training (CPT) enables Large Language Models (LLMs) to acquire second-language capabilities, yet the mechanisms underlying CPT remain poorly understood. |
| Approach: | They investigate how CPT adapts model representations across diverse language families and scripts, model sizes, and architectures. |
| Outcome: | The proposed model can be surgically transferred between base and CPT models with minimal loss. |
Schema-based Data Augmentation for Event Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing data augmentation methods rely on language models to train event extraction models. |
| Approach: | They propose a schema-based data augmentation method that utilizes event schemas to guide the data generation process. |
| Outcome: | The proposed method produces high-quality generated data and significantly improves model performance. |
Do Language Models Have Semantics? On the Five Standard Positions (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are trained to solve the so-called cloze task . solving clozing tasks is essentially a memorization task, says a recent study . |
| Approach: | They propose to use five positions to determine whether large language models exhibit semantic understanding . large language model is trained to solve the so-called cloze task . |
| Outcome: | The proposed theory is based on a pairwise comparison of five positions on semantic understanding in large language models and chatbots. |
PROOD: A Simple LLM Out-of-Distribution Guardrail Leveraging Response Semantics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing OOD methods often struggle with deliberately obfuscated, context-dependent, or superficially benign prompts. |
| Approach: | They propose a framework that jointly analyzes LLM prompts and their outputs to improve semantic understanding. |
| Outcome: | The proposed framework outperforms existing OOD methods on three benchmarks and improves F1 scores by up to 6.3 points. |
Probing Semantic Alignment, Lexical Invariance, and Syntactic Influence in LLM Metaphor Processing (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) achieve strong performance on metaphor detection and interpretation tasks, yet it remains unclear what such success actually reveals about metaphor processing. |
| Approach: | They propose to probing semantic attribute alignment, lexical invariance, and syntactic sensitivity to examine the limits of behavioral evidence for metaphor processing. |
| Outcome: | The proposed model can exhibit semantic drift relative to reference attributes, stable lexical anchors persist across contextual conditions, potentially supporting conventional metaphors while biasing novel metaphors requiring contextual integration. |
Enhanced Noun-Noun Compound Interpretation through Textual Enrichment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent benchmarks frame Noun-Noun Compound Interpretation as a multiple-choice question . but, it still faces key limitations: vague relation descriptions as options and inability to handle polysemous compounds. |
| Approach: | They propose a textual enrichment framework that parses relations into eventoriented descriptions . the framework explicitly surfaces the hidden event connecting head and modifier . |
| Outcome: | The proposed framework yields consistently higher accuracy across three LLM families. |
LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-intent utterances processing remains a persistent challenge due to intricate intent-slot dependencies and semantic ambiguities. |
| Approach: | They propose a label-aware contrastive attention network (LCAN) that integrates label-based attention and contrastive learning strategies to improve semantic understanding and generalization in multi-intent scenarios. |
| Outcome: | The proposed model improves intent recognition and slot filling performance in multi-intent dialogue systems. |
Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models (2026.findings-acl)
Copied to clipboard
Mohammad Mahdi Abootorabi, Omid Ghahroodi, Anas Madkoor, Marzia Nouri, Doratossadat Dastgheib, Ehsaneddin Asgari
| Challenge: | Existing evaluations focus on piecemeal or disconnected tasks, obscuring critical cognitive weaknesses and providing little insight for targeted improvement. |
| Approach: | They propose a bilingual, cognitively human-grounded multimodal benchmark for VLMs that evaluates six levels of cognition through carefully designed image–question–answer tasks. |
| Outcome: | The proposed framework ensures scalability, cultural inclusivity, and linguistic fidelity. |
UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies rely on shallow unsupervised data generated by token surface matching regardless of global context-aware semantics of the surrounding text tokens. |
| Approach: | They propose an Unsupervised Pseudo Semantic Data Augmentation mechanism to enrich training data without human intervention. |
| Outcome: | The proposed model improves on general zero-shot cross-lingual understanding tasks on different languages without human intervention. |
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark (2025.acl-long)
Copied to clipboard
Navve Wasserman, Roi Pony, Oshri Naparstek, Adi Raz Goldfarb, Eli Schwartz, Udi Barzelay, Leonid Karlinsky
| Challenge: | Existing benchmarks do not fully capture real-world retrieval challenges . existing benchmarks lack a complete understanding of how models perform in realistic setups . |
| Approach: | They propose an automatic benchmark to address four key properties essential for real-world retrieval: (i) multi-modal documents, (ii) enhanced difficulty, ( (iv) Realistic-RAG queries and (v) accurate labeling. |
| Outcome: | The proposed model reveals significant model weaknesses, particularly in handling table-heavy documents and robustness to query rephrasing. |
X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-to-video retrieval systems use embedding models for feature extraction and compute cosine similarities for ranking. |
| Approach: | They propose an explainable retrieval framework upon LLM CoT reasoning to replace embedding models for feature extraction and ranking. |
| Outcome: | The proposed retrieval framework improves retrieval performance and produces detailed rationales. |
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)
Copied to clipboard
Feng Jiang, Zhiyu Lin, Yiyang Liu, Liumeng Xue, Fan Bu, Yuhao Du, Xiangying Chen, Benyou Wang, Haizhou Li
| Challenge: | Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits. |
| Approach: | They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression. |
| Outcome: | The proposed system enables more natural, robust, and human-aligned speech agents. |
MiniRAG: A Lightweight RAG system with Small Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RAG frameworks rely on Large Language Models (LLMs) for all stages of the process, resulting in high computational costs and resource demands. |
| Approach: | They propose a semantic-aware heterogeneous graph indexing mechanism that combines text chunks and named entities in a unified structure and a lightweight topology-enhanced retrieval approach that leverages graph structures for efficient knowledge discovery without requiring advanced language capabilities. |
| Outcome: | The proposed system achieves comparable performance to LLM-based methods while requiring only 25% of the storage space. |
WojoodRelations: Arabic Relation Extraction Corpus and Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on Arabic RE remains limited due to the language’s rich morphology and syntactic complexity, and the lack of large, high-quality datasets. |
| Approach: | They propose to use WojoodRelations to extract relation relationships from Arabic textual data using relation-aware templates and GPT-Joint to perform relation-based retrieval. |
| Outcome: | The proposed method achieves a Cohen’s of 0.92, indicating high reliability, and supervised models achieve 92.89% F1 for RE, while LLMs obtain 72.73% F1 . |
TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding (2026.acl-long)
Copied to clipboard
| Challenge: | a critical ambiguity persists regarding what constitutes "joint ASR and diarization" a unified framework for multi-speaker ASR is proposed, but it is not yet clear what constitute "diarization." |
| Approach: | They propose a unified LLM-based framework that uses Temporal Anchor Grounding for joint multi-speaker ASR and diarization. |
| Outcome: | The proposed framework improves on AMI and AliMeeting benchmarks on speaker-content alignment . the proposed framework achieves consistent improvements in Diarization Error Rate over strong baselines . |
LLMs are Brittle to Simple Code Transformations: Introducing CETBench – A Benchmark for Code-Equivalence Checking (2026.findings-acl)
Copied to clipboard
| Challenge: | a new benchmarking tool for code equivalence checks the performance of LLMs. |
| Approach: | They propose a code-equivalence with transformations benchmark built from a repository of programs that may solve the same or different tasks. |
| Outcome: | The proposed approach boosts performance on the transformed pairs of programs. |
HSGraphAgent: Knowledge-Graph-Guided Large Language Models for Harmonized System Code Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Harmonized System (HS) code classification is a hierarchically structured and regulation-constrained task, often complicated by short and noisy product descriptions. |
| Approach: | They propose a knowledge-graph-guided LLM framework that formulates HS classification as a stepwise, regulation-aware reasoning process over an explicit HS knowledge graph. |
| Outcome: | The proposed framework constrains inference to legally valid paths while producing explicit and traceable reasoning trajectories. |
SURE or Not? Investigating Semantic Understanding in Dense Retrieval Models (2026.acl-long)
Copied to clipboard
| Challenge: | Dense retrieval models have been successful in a number of applications but it is unclear whether they truly understand semantics. |
| Approach: | They propose a benchmark for semantic understanding in dense retrieval that characterizes semantic precision, semantic abstraction and semantic equivalence along three dimensions. |
| Outcome: | The proposed model characterizes semantic understanding in dense retrieval along three dimensions: semantic precision, semantic abstraction, and semantic equivalence. |