Papers with evaluation metric
I Don’t Need Solution. I Need Emotional Support : Empathetic LLMs based on Emotional Validation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) struggle to generate emotional support response, despite observing and reflecting on the help-seeker’s situation . Empathy drives the formation of constructive interpersonal and supportive relationships, including counseling for mental health care . |
| Approach: | They propose to use a two-stage training process to enhance empathetic response generation through empathy acquisition and emotional validation alignment. |
| Outcome: | The proposed method significantly improves empathetic response generation, achieving superior performance in both automatic and human evaluations. |
Summary Level Training of Sentence Rewriting for Abstractive Summarization (D19-54)
Copied to clipboard
| Challenge: | Existing models rely on sentence-level rewards or suboptimal labels to achieve summary-level ROUGE scores. |
| Approach: | They propose a model that extracts salient sentences from a document and paraphrases them to generate a summary. |
| Outcome: | The proposed model improves on CNN/Daily Mail and New York Times datasets. |
JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics for text simplification focus on only one dimension: fluency, simplicity and meaning preservation. |
| Approach: | They introduce a dataset to assess legal meaning preservation between two legal texts . they also introduce sanity checks for two identical sentences . |
| Outcome: | The proposed metric shows superior correlation with human judgment compared to existing metrics. |
Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection (2020.coling-main)
Copied to clipboard
| Challenge: | Existing work on identifying the salient information in a text has used a limited representation of events that omits essential information. |
| Approach: | They propose a highly contextual model of event salience that uses a rich representation of events and integrates document-level information. |
| Outcome: | The proposed model improves on an event salience dataset by 2-4% on standard metrics and addresses flaws in existing evaluation methodologies. |
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs (2025.naacl-long)
Copied to clipboard
Do Xuan Long, Ngoc-Hai Nguyen, Tiviatis Sim, Hieu Dao, Shafiq Joty, Kenji Kawaguchi, Nancy F. Chen, Min-Yen Kan
| Challenge: | Using format-following capabilities, state-of-the-art large language models (LLMs) can be leveraged to tailor outputs to specific task formats. |
| Approach: | They propose to define a format bias evaluation metric and establish effective strategies to reduce it. |
| Outcome: | The proposed evaluation reduces the variance in ChatGPT’s performance among wrapping formats from 235.33 to 0.71 (%2) |
Neural Math Word Problem Solver with Reinforcement Learning (C18-1)
Copied to clipboard
| Challenge: | Existing models for solving math word problems rely on predefined rules or feature engineering. |
| Approach: | They propose to incorporate copy and alignment mechanism into the sequence-to-sequence model to address two shortcomings . they use model output as a feature and incorporate it into the feature-based model to explore the effectiveness . |
| Outcome: | The proposed model outperforms the state-of-the-art models on the problem solving task. |
MoNoise: A Multi-lingual and Easy-to-use Lexical Normalization Tool (P19-3)
Copied to clipboard
| Challenge: | In this paper, we demonstrate the online demo and command line interface of a lexical normalization system (MoNoise) for a variety of languages. |
| Approach: | They propose to bundle seven datasets in six languages to form a new benchmark and a novel evaluation metric which is particularly suitable for cross-dataset comparisons. |
| Outcome: | The proposed model is based on the original word and features from the original language for each normalization candidate. |
Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances (2022.acl-short)
Copied to clipboard
| Challenge: | Dialogue State Tracking (DST) is a task-oriented conversational agent that keeps track of key information exchanged during a conversation. |
| Approach: | They propose a new evaluation metric called Flexible Goal Accuracy to address shortcomings of JGA. |
| Outcome: | The proposed metric improves on existing metrics and improves performance of turn-level and non-cumulative belief state models. |
English-to-Chinese Transliteration with Phonetic Auxiliary Task (2020.aacl-main)
Copied to clipboard
| Challenge: | Several NMT techniques have been used to enhance machine transliteration models, but few focus on the linguistic features specific to the relevant languages. |
| Approach: | They propose a phonetic auxiliary task that integrates phonetic features into a model to improve generalization performance of the main transliteration task. |
| Outcome: | The proposed model achieves similar performance to the current state of the art with a much smaller size. |
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning (2024.findings-acl)
Copied to clipboard
Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji
| Challenge: | LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much . |
| Approach: | They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis . |
| Outcome: | The proposed model outperforms current models in evaluating caption factuality. |
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach (2024.acl-long)
Copied to clipboard
| Challenge: | primarily addressed in text-to-image retrieval task using dialogue-form context query . conventionally, text-based retrieval methods rely on initial text descriptions . |
| Approach: | They propose a plug-based retrieval method that uses large language models as questioners to generate non-redundant questions about the attributes of the target image. |
| Outcome: | The proposed method performs better than zero-shot and fine-tuned baselines in benchmarks. |
DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing logic reasoning benchmarks are limited in language diversity and their distributions are deviated from ideal distributions, which may lead to biased evaluation results. |
| Approach: | They propose a new logic benchmark DivLogicEval that uses natural sentences to evaluate logical reasoning . |
| Outcome: | The proposed evaluation metric mitigates bias and randomness inherent in LLMs. |
CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality (2022.findings-naacl)
Copied to clipboard
| Challenge: | Specific problems arise when translating from English into languages with formality markers, such as “Are you sure?” . Using wrong or inconsistent tone may be perceived as inappropriate or jarring for users of certain cultures and demographics. |
| Approach: | They propose to train formality-controlled models by fine-tuning on labeled contrastive data and a metric to evaluate them. |
| Outcome: | The proposed model achieves high accuracy (82% in-domain and 73% out-of-domain) while maintaining overall quality. |
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics are not capable of evaluating text quality. |
| Approach: | They propose a metric that compares system output against reference texts based on semantics rather than surface forms. |
| Outcome: | The proposed metric shows a high correlation with human judgment of text quality on a number of text generation tasks. |
Re-Examining FactBank: Predicting the Author’s Presentation of Factuality (2022.coling-1)
Copied to clipboard
| Challenge: | Previously published results on FactBank are no longer valid. |
| Approach: | They propose to correct a subset of FactBank data to improve performance . they use multiple training paradigms, data smoothing techniques, and polarity classifiers . |
| Outcome: | The proposed model improves performance on the FactBank dataset. |
RAP: A Metric for Balancing Repetition and Performance in Open-Source Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models generate repetitive content, leading to incomplete or fragmented responses, which can negatively affect user experience. |
| Approach: | They propose a new evaluation metric that quantifies and integrates repetition penalty into the assessment of model performance, enabling tuning of RPP. |
| Outcome: | The proposed evaluation metric reduces repetition while minimizing performance loss. |
Detect, Disambiguate, and Translate: On-Demand Visual Reasoning for Multimodal Machine Translation with Large Vision-Language Models (2025.naacl-long)
Copied to clipboard
Danyang Liu, Fanjie Kong, Xiaohang Sun, Dhruva Patil, Avijit Vajpayee, Zhu Liu, Vimal Bhat, Najmeh Sadoughi
| Challenge: | Multimodal machine translation (MMT) aims to leverage additional modalities beyond text . current MMT systems rely heavily on monolingual English captioning data . |
| Approach: | They propose a reasoning-based framework to leverage large-scale vision-language models for MMT . they propose Detect, Disambiguate, and Translate framework to detect ambiguity in input sentence . |
| Outcome: | The proposed framework outperforms state-of-the-art models in disambiguation accuracy and translation quality. |
Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation (N18-2)
Copied to clipboard
| Challenge: | Existing machine translation evaluation metrics use synonyms and paraphrases to reward meaning-equivalent but lexically divergent translations. |
| Approach: | They propose a machine translation evaluation metric which exploits reference translations enriched with meaning equivalent expressions. |
| Outcome: | The proposed metric achieves medium performance on large and noisier datasets . it is compared with the existing HyTER evaluation metric . |
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies have developed watermarking algorithms which restrict the generation process to leave an invisible trace for watermark detection. |
| Approach: | They propose a benchmarking procedure that compares different methods to ensure consistent watermarking strength and jointly evaluates their generation and detection performance. |
| Outcome: | The proposed benchmark compares 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observes the common struggles for current methods on maintaining the generation quality. |
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for target-guided response generation are inconsistent with human judgement ratings. |
| Approach: | They propose a technique that finds a bridging path between the source and target and uses it to generate transition responses. |
| Outcome: | The proposed technique outperforms baselines on target-guided response generation task. |
VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on object hallucinations, focusing on object outputs . current evaluation methods struggle to address subtle semantic distinctions between outputs and reference data . |
| Approach: | They propose a multi-dimensional benchmark covering objects, attributes, and relations . they propose metric that generalizes CHAIR metric and incorporates faithfulness and coverage . |
| Outcome: | The proposed evaluation framework is more comprehensive and better correlated with humans than existing evaluation methods. |
DA3: A Distribution-Aware Adversarial Attack against Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent attacks have shown that adversarial examples have a different data distribution than the original examples, reducing their effectiveness under detection methods. |
| Approach: | They propose a distribution-aware adversarial attack method that considers the distribution shifts of adversarials to improve attacks’ effectiveness under detection methods. |
| Outcome: | The proposed method improves the effectiveness of adversarial examples under detection methods and integrates both ASR and detectability. |
Instruction Induction: From Few Examples to Natural Language Task Descriptions (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models can perform unseen tasks by conditioning on a few input-output demonstrations, but task inference is implicit and the ability of models to explicitly reason about it remains unexplored. |
| Approach: | They propose an instruction induction challenge in which a model is asked to generate a natural language instruction that fits a set of labeled examples. |
| Outcome: | The proposed model achieves 65.7% of human performance while the original model only reaches 9.8% of human performances. |
Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have not investigated the differences between different correlation measures in meta-evaluation. |
| Approach: | They analyze 12 common correlation measures using real-world data from six widely-used NLG evaluation datasets and 32 evaluation metrics. |
| Outcome: | The proposed measures exhibit the best performance in discriminative power and ranking consistency . the measures using system-level grouping or Kendall correlation are the least sensitive to score granularity . |
What just happened? Evaluating retrofitted distributional word vectors (N19-1)
Copied to clipboard
| Challenge: | Recent work has attempted to enhance vector space representations using information from structured semantic resources. |
| Approach: | They propose a root-mean-square error evaluation metric to evaluate the utility of different lexical resources for retrofitting. |
| Outcome: | The proposed method improves word similarity performance by using root-mean-square error (RMSE) and root-macro-error (RMME) metric. |
Rethinking Sentiment Style Transfer (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods for text style transfer are unsatisfactory. |
| Approach: | They propose to use a graph-based method to extract attribute content from sentences . they propose an efficient regularization to leverage attribute-dependent content as guiding signals. |
| Outcome: | The proposed method is based on a YELP and IMDB dataset and it is able to detect errors in the human evaluation. |
“According to . . . ”: Prompting Language Models Improves Quoting from Pre-Training Data (2024.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) may hallucinate and generate false information despite pre-training on factual data. |
| Approach: | They propose a new evaluation metric that measures the extent to which model-produced answers are directly found in underlying text corpora. |
| Outcome: | The proposed evaluation metric measures the extent to which model-produced answers are directly found in underlying text corpora. |
ICE-Score: Instructing Large Language Models to Evaluate Code (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. |
| Approach: | They propose a new evaluation metric by instructing large language models for code assessments using a set of programming languages. |
| Outcome: | The proposed evaluation metric surpasses state-of-the-art metrics for code generation, delivering high levels of accuracy and consistency across programming languages and tasks. |
A Retrospective Analysis of the Fake News Challenge Stance-Detection Task (C18-1)
Copied to clipboard
Andreas Hanselowski, Avinesh PVS, Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, Iryna Gurevych
| Challenge: | 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. |
| Approach: | They propose a new evaluation metric favoring the majority class, which can be easily classified, and propose stacked LSTM models that perform on par with the best systems, but is superior in predicting minority classes. |
| Outcome: | The proposed evaluation metric favors the majority class, which can be easily classified, and overestimates the true discriminative power of the methods. |
Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies on open-domain conversational systems are limited to single corpus training and evaluation. |
| Approach: | They propose a method which encodes each corpus through a unique corpus embedding and a new word-level importance weighting method that integrates DF to the loss function. |
| Outcome: | The proposed methods gain significant improvements on both automatic and human evaluation. |
Unifying Human and Statistical Evaluation for Natural Language Generation (N19-1)
Copied to clipboard
| Challenge: | Human evaluation captures quality but fails to capture diversity . statistical evaluation fails to catch models that plagiarize from training set . |
| Approach: | They propose a framework which evaluates both diversity and quality based on the optimal error rate of predicting whether a sentence is human-generated. |
| Outcome: | The proposed framework evaluates diversity and quality on summarization and chit-chat dialogue. |
Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description (2025.findings-naacl)
Copied to clipboard
Mahshid Dehghani, Amirahmad Shafiee, Ali Shafiei, Neda Fallah, Farahmand Alizadeh, Mohammad Mehdi Gholinejad, Hamid Behroozi, Jafar Habibi, Ehsaneddin Asgari
| Challenge: | Existing 3D facial emotion modeling models are constrained by limited emotion classes and insufficient datasets. |
| Approach: | They propose a 3D facial emotion modeling dataset that spans a wide spectrum of human emotions . they use large language models to generate a diverse array of textual descriptions . |
| Outcome: | Emo3D is an extensive dataset that spans human emotions with images and 3D blendshapes. |
Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness (N18-1)
Copied to clipboard
| Challenge: | Currently, state-of-the-art models achieve impressive test set performance in the form of accuracy scores. |
| Approach: | They examine the models' robustness to semantically-valid alterations to the input data by identifying three factors and comparing their impact on three SNLI models. |
| Outcome: | The proposed models show that they can generalise to new in-domain instances while also showing that they suffer from insensitivity to small but semantically significant alterations. |
Cross-lingual Decompositional Semantic Parsing (D18-1)
Copied to clipboard
| Challenge: | Renewed interest in semantic analysis has led to a surge of proposed new frameworks . many of these efforts are limited to the analysis of English, but with a number of exceptions e.g., recent efforts in Minimal Recursion Semantics (MRS) and multilingual FrameNet annotation and parsing. |
| Approach: | They propose a cross-lingual decompositional semantic analysis task based on a target language . they propose 'end-to-end' model with an annotating mechanism that supports intra-sentential coreference . |
| Outcome: | The proposed model outperforms baselines by at least 1.75 F1 score on an evaluation dataset. |
MPCoder: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing Large Language Models are usually generalized with large programming corpus, therefore the generated code is difficult to adapt to personalized and/or customized requests. |
| Approach: | They propose a method to use Large Language Models to generate personalized code for multiple users. |
| Outcome: | The proposed model can generate personalized code for multiple users . it can be used to improve code generation and reduce maintenance costs. |
On the Evaluation Metrics for Paraphrase Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics for paraphrase generation are not designed for the task, but adopted from other evaluation tasks. |
| Approach: | They propose a new evaluation metric for paraphrase generation that uses reference-based and reference-free metrics. |
| Outcome: | The proposed evaluation metric outperforms existing metrics and is more reliable than reference-based metrics. |
Probabilistic Robustness for Data Filtering (2023.eacl-main)
Copied to clipboard
| Challenge: | Modern machine learning works with massive amounts of data on a range of tasks like language modeling, object detection, and data mining. |
| Approach: | They propose a probabilistic robustness rewarded data optimization approach to enhance the model's generalization power by selecting training data that optimizes probabilistic metrics. |
| Outcome: | The proposed approach achieves +17.2% increase of accuracy and -28.05 decrease of perplexity on unknown-domain test sets. |
How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence. |
| Approach: | They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation. |
| Outcome: | The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models. |
Incremental Beam Manipulation for Natural Language Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | a larger beam size can lead to deteriorating performance of natural language generation systems due to model errors . performance of NLG systems can plateau or even decrease when beam sizes larger than 10 are used . |
| Approach: | They propose to rerank the output of beam search to produce a good set of hypotheses . they propose incremental beam manipulation to discarded hypothese . |
| Outcome: | The proposed method outperforms a strong reranker on the E2E and WebNLG datasets while being on par with the existing method. |
FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent model-based reference-free metrics for open-domain dialogue evaluation lack correlations with human judgment and poor interpretability. |
| Approach: | They propose a multi-dimensional dialogue-level metric with three sub-metrics targeting a specific dimension. |
| Outcome: | The proposed metric outperforms existing models and sub-metrics in three high-quality dialogue evaluation benchmarks. |
MQM-Chat: Multidimensional Quality Metrics for Chat Translation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for chat translation face challenges due to high levels of ambiguity and stylized contents. |
| Approach: | They propose a multidimensional quality metric for chat translation that includes seven error types . they use human annotations to analyze chat data generated by five translation models . |
| Outcome: | The proposed evaluation metric can qualify errors while highlighting chat-specific issues explicitly. |
FLEX: Expert-level False-Less EXecution Metric for Text-to-SQL Benchmark (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods for text-to-SQL systems show many false positives and negatives . however, the Execution Accuracy (EX) metric is flawed and can diverge from human experts. |
| Approach: | They propose a method to evaluate text-to-SQL systems using large language models to emulate human expert-level evaluation of SQL queries. |
| Outcome: | The proposed metric improves agreement with human experts with comprehensive context and sophisticated criteria. |
Evaluating Text GANs as Language Models (N19-1)
Copied to clipboard
| Challenge: | Generative Adversarial Networks (GANs) do not suffer from the problem of exposure bias. |
| Approach: | They propose to approximate the distribution of text generated by a GAN and compare it to traditional probability-based LM metrics. |
| Outcome: | The proposed method performs significantly worse than state-of-the-art LMs on several GAN-based models and can accelerate progress in GAN text generation. |
Systematic Task Exploration with LLMs: A Study in Citation Text Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) provide unprecedented flexibility in defining and executing complex, creative natural language generation tasks. |
| Approach: | They propose a framework that consists of input manipulation, reference data, and output measurement to explore citation text generation. |
| Outcome: | The proposed framework explores citation text generation, a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric and has not yet been tackled within the LLM paradigm. |
Advocating Character Error Rate for Multilingual ASR Evaluation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Word error rate (WER) has been used for automatic speech recognition (ASR) evaluations for English datasets for many years. |
| Approach: | They propose to use the character error rate as the primary metric in multilingual ASR evaluation to account for morphologically complex languages. |
| Outcome: | The character error rate (CER) is the primary evaluation metric in multilingual ASR evaluation. |
Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | ChatGPT and GPT-4 are popular as evaluation metric for complex generative tasks . however, they are not ready as human replacements due to significant limitations . |
| Approach: | They conduct extensive analysis to examine the stability and reliability of LLMs as automatic evaluators for abstractive summarization. |
| Outcome: | The proposed methods outperform the commonly used automatic metrics but are not ready for human evaluation due to significant limitations. |
Generative Pretraining for Paraphrase Evaluation (2022.acl-long)
Copied to clipboard
| Challenge: | ParaBLEU is a paraphrase representation learning model and evaluation metric for text generation. |
| Approach: | They propose a paraphrase representation learning model and evaluation metric for text generation that uses generative conditioning as a pretraining objective. |
| Outcome: | The proposed model outperforms existing models on the 2017 WMT Metrics Shared Task using only 50% of the available training data and surpasses BLEU, ROUGE and METEOR with only 40 examples. |
Towards Domain-Independent Text Structuring Trainable on Large Discourse Treebanks (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Text structuring is a fundamental step in natural language generation, especially when generating multi-sentential text. |
| Approach: | They propose a novel task that combines neural dependency tree induction with pointer networks to train on large discourse treebanks. |
| Outcome: | The proposed method outperforms existing content ordering metrics and outperformed existing ones. |
Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on how large language model agents collaborate with humans in equal roles emphasize the importance of coordination and communication. |
| Approach: | They propose to use chain-of-thought prompts to evaluate different collaboration perspectives, from independent to more complex, dependent tasks. |
| Outcome: | The proposed model significantly improves the evaluation metric. |
BEMEAE: Moving Beyond Exact Span Match for Event Argument Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Event Argument Extraction (EAE) is a complex task that requires deep comprehension of text to accurately identify and classify event arguments. |
| Approach: | They propose a new evaluation metric that integrates deterministic components with a semantic matching component for more accurate assessment. |
| Outcome: | The proposed evaluation metric leads to higher F1 scores and significant changes in model rankings, underscoring ESM’s inadequacy for comprehensive evaluation of EAE. |
An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | Pre-trained word embeddings have been shown to improve the performance of neural networks across a wide variety of tasks. |
| Approach: | They propose two new metrics to understand the downstream reliability of word embeddings. |
| Outcome: | The proposed model can improve performance with slight changes to the training data, but it can also fail with multiple neural network architectures. |
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question answering datasets lack numerical reasoning and reasoning processes . current research on numerical reasoning focuses on simple calculations . |
| Approach: | They propose a conversational and bilingual question answering dataset with numerical reasoning with compound mathematical expressions. |
| Outcome: | The proposed model achieves 55.5 exact match scores while human performance is 89.7. |
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback (2025.acl-long)
Copied to clipboard
Lester James Validad Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi
| Challenge: | Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. |
| Approach: | They propose a Hybrid Preference routER that defers an annotation to either humans or LMs, achieving better annotation quality while reducing the cost of human-only annotation. |
| Outcome: | The proposed model achieves better annotation quality while reducing the cost of human-only annotation. |
Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)
Copied to clipboard
Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong
| Challenge: | a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias. |
| Approach: | They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness . |
| Outcome: | The proposed evaluation metric is based on two components: desirability and information mass. |
Over-Searching in Search-Augmented Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. |
| Approach: | They conduct a systematic evaluation of over-searching across multiple dimensions including query types, model categories, retrieval conditions, and multi-turn conversations. |
| Outcome: | The proposed model improves answer accuracy on answerable queries but harms abstention on unanswerable ones . |
On the Emotion Understanding of Synthesized Speech (2026.acl-long)
Copied to clipboard
Yuan Ge, Haishu Zhao, AoKai Hao, Junxiang Zhang, Bei Li, Xiaoqian Liu, Chenglong Wang, Jianjin Wang, Bingsen Zhou, Bingyu Liu, JingBo Zhu, Zhengtao Yu, Tong Xiao
| Challenge: | Existing models for emotion understanding do not capture fundamental features of synthesized speech. |
| Approach: | They evaluate emotion recognition models on synthesized speech using SER models and generative models. |
| Outcome: | The proposed model can't generalize to synthesized speech because of speech token prediction . generative models tend to infer emotion from textual semantics while ignoring paralinguistic cues. |
Content Explorer: Recommending Novel Entities for a Document Writer (D18-1)
Copied to clipboard
| Challenge: | Existing tools for exploratory search can be useful for document writers but they are not always effective for identifying topics for further research. |
| Approach: | They propose a supervised learning problem for recommending topics to a writer . they propose entropy loss function modification to improve the results . |
| Outcome: | The proposed model improves on a large dataset and can be used to identify topics for further research. |
CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Evaluating the performance of Grammatical Error Correction systems is a challenging task due to its subjectivity. |
| Approach: | They propose a method to evaluate GEC systems in multi-reference evaluation setting . they use consistent edit boundaries to eliminate bias caused by inconsistent edit boundaries . |
| Outcome: | The proposed evaluation metric eliminates bias caused by inconsistent edit boundaries on six English reference sets. |
RoMe: A Robust Metric for Evaluating Natural Language Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Empirical results suggest that RoMe has a stronger correlation to human judgment over state-of-the-art metrics in evaluating system-generated sentences across several NLG tasks. |
| Approach: | They propose an automatic evaluation metric incorporating several core aspects of natural language understanding (language competence, syntactic and semantic variation). |
| Outcome: | The proposed evaluation metric is trained on language features such as semantic similarity combined with tree edit distance and grammatical acceptability, using a self-supervised neural network. |
CAIRE: Cultural Attribution of Images with Retrieval (2026.eacl-long)
Copied to clipboard
| Challenge: | Current text-to-image models produce homogeneous outputs given under-specified prompts and their outputs are disproportionately biased toward Western cultures. |
| Approach: | They propose a framework that assesses the degree of cultural relevance of an image, given a user-defined set of labels. |
| Outcome: | The proposed evaluation metric surpasses baselines on a manually curated dataset of culturally salient but rare items built using language models by 22% F1 points. |
Question Answering as an Automatic Evaluation Metric for News Article Summarization (N19-1)
Copied to clipboard
| Challenge: | Recent work on summarization and headline generation focuses on maximizing ROUGE scores. |
| Approach: | They propose an extrinsic evaluation metric that maximizes ROUGE scores for automatic summarization and headline generation. |
| Outcome: | The proposed model maximizes ROUGE scores while increasing competitive results. |
LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals (2026.findings-acl)
Copied to clipboard
| Challenge: | Concept-based explanations quantify how high-level concepts influence model behavior . existing benchmarks rely on costly human-written counterfactuals that serves as imperfect proxy . |
| Approach: | They propose a framework for constructing datasets containing structural counterfactual pairs . they use a structured Causal Model to generate a concept-based explanation . |
| Outcome: | The proposed framework compares concept-based explanations to causal effects estimated from counterfactuals. |
Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)
Copied to clipboard
Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang
| Challenge: | GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs. |
| Approach: | They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training. |
| Outcome: | The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o . |
Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output (2024.naacl-long)
Copied to clipboard
| Challenge: | Multimodal summarization with multimodal output (MSMO) has attracted increasing research interest . evaluation is an emerging yet underexplored research topic . |
| Approach: | They propose a framework that studies three research questions of MSMO evaluation . they propose an automatic evaluation metric and a meta-evaluation benchmark dataset . |
| Outcome: | The proposed evaluation metric and human-annotated meta-evaluation benchmark are used to assess the quality of evaluation metrics and show the framework is effective. |
SemBleu: A Robust Metric for AMR Parsing Evaluation (P19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism where the meaning of a sentence is encoded as a rooted, directed graph. |
| Approach: | They propose a metric that extends SMATCH to parse AMRs and does not suffer from search errors. |
| Outcome: | The proposed metric does not suffer from search errors and considers non-local correspondences in addition to local ones. |
OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Tracking (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work on state tracking assumes both entities and state space are known, which limits their applicability. |
| Approach: | They propose a two-stage model that refines the state change prediction conditioned on entities predicted from the first stage. |
| Outcome: | The proposed model improves on the cleaned dataset and the evaluation metric on the proposed model. |
Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing leaderboards are incomplete and some contain incorrect information. |
| Approach: | They propose a manually-curated Scientific Leaderboard dataset that overcomes these problems . they propose three experimental settings where TDM triples are fully defined, partially defined, or undefined . |
| Outcome: | The proposed system overcomes the shortcomings of existing leaderboard datasets . it can be used to evaluate and compare scientific methods, but it requires manual labor . |
Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for summarizing arguments are incapable of distinguishing between generated key points of different qualities. |
| Approach: | They propose an extractive approach that generates concise, high quality key points . they propose to use a clustering approach to generate key points from raw arguments . |
| Outcome: | The proposed method outperforms state-of-the-art methods for key point generation . it offers concise, high quality generated key points with higher coverage of reference summaries . |
SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)
Copied to clipboard
Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye
| Challenge: | Chain-of-Thought prompting improves the math reasoning capability of large language models. |
| Approach: | They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity. |
| Outcome: | The proposed method reduces computational complexity and provides robust correlations with model performance. |
Fact-based Content Weighting for Evaluating Abstractive Summarisation (2020.acl-main)
Copied to clipboard
| Challenge: | Abstractive summarisation is notoriously hard to evaluate since word-overlap-based metrics are insufficient. |
| Approach: | They propose a new evaluation metric which is based on fact-level content weighting, relating the facts of the document to the facts in the summary. |
| Outcome: | The proposed evaluation metric is highly correlated to human perception and compares favourably to the recent manual highlight-based metric of Hardy et al. |
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents (2024.acl-long)
Copied to clipboard
Shihan Deng, Weikai Xu, Hongda Sun, Wei Liu, Tao Tan, Liujianfeng Liujianfeng, Ang Li, Jian Luan, Bin Wang, Rui Yan, Shuo Shang
| Challenge: | Existing benchmarks for LLM-based mobile agents are insufficient to evaluate their capabilities. |
| Approach: | They propose a benchmark to evaluate LLM-based mobile agents' planning capabilities . they expand UI operations by incorporating 103 APIs to accelerate task completion . |
| Outcome: | The proposed benchmarks are based on 103 collected APIs and real user queries . the data is categorized into three distinct groups: SAST, SAMT, and MAMT . |
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing learning metrics are limited to tasks where large human ratings are available. |
| Approach: | They propose a model-based natural language generation (NLG) evaluation metric that is highly correlated with human judgements without requiring human annotation. |
| Outcome: | The proposed metric outperforms all prior unsupervised metrics on multiple NLG tasks including translation, image captioning, and WebNLG text generation. |
Automatic Evaluate Dialogue Appropriateness by Using Dialogue Act (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluations of dialogue quality rely on human judgments, which are time-consuming, labor-intensive, prone to biases, and lacking objectivity. |
| Approach: | They propose a method that utilizes the underlying patterns of dialogue act transitions to evaluate the appropriateness of chatbot responses. |
| Outcome: | The proposed method proves that human judgments are time-consuming, labor-intensive, and lacking objectivity. |
Subword Language Model for Query Auto-Completion (D19-1)
Copied to clipboard
| Challenge: | Current neural query auto-completion systems rely on character-level language models but they slow down when queries are long. |
| Approach: | They propose to use subword language models for query auto-completion . they propose to implement a retrace algorithm and a method for approximate marginalization . |
| Outcome: | The proposed model achieves 2.5 times faster while maintaining similar quality to character-level baseline. |
An Evaluation Framework for Legal Document Summarization (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing metrics for summarizing legal documents fail to evaluate intent in the original text. |
| Approach: | They propose an automated intent-based summarization metric which shows a better agreement with human evaluation as compared to other automated metrics like BLEU, ROUGE-L etc. |
| Outcome: | The proposed method shows that human evaluation is more accurate than other metrics. |
Gender Biases in Automatic Evaluation Metrics for Image Captioning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained evaluation metrics can perpetuate and amplify biases, causing inability to differentiate between biased and unbiased generations. |
| Approach: | They conduct a systematic study of gender biases in image captioning tasks . they show that pretrained models perpetuate and amplify biase . |
| Outcome: | The proposed model-based evaluation metrics have shown good correlations with human judgments in language generation tasks. |
Designing a Collaborative Process to Create Bilingual Dictionaries of Indonesian Ethnic Languages (L18-1)
Copied to clipboard
| Challenge: | a constraint-based approach has been proven useful for inducing bilingual dictionary for low-resource languages. |
| Approach: | They propose a constraint-based approach for inducing bilingual dictionary for low-resource languages . they propose heuristic plan that only utilizes manual investment by native speaker . |
| Outcome: | The proposed approach outperforms the heuristic plan with 63.3% cost reduction. |
SyllabusQA: A Course Logistics Question Answering Dataset (2024.acl-long)
Copied to clipboard
| Challenge: | We introduce Fact-QA, an LLM-based evaluation metric to evaluate the factuality of predicted answers. |
| Approach: | They propose to use an open-source dataset to analyze logistics-related question-answer pairs in a logistics-based course. |
| Outcome: | The proposed approach performs close to humans on traditional metrics of textual similarity, but there is a significant gap between them and humans in terms of fact precision. |
Measuring What Matters: Evaluating Ensemble LLMs with Label Refinement in Inductive Coding (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are prone to inconsistencies and individual biases, limiting their reliability. |
| Approach: | They propose a framework that combines ensemble methods with code refinement methodology to address these challenges. |
| Outcome: | The proposed framework outperforms large language models and LLMs with a low-rank averaging and a moderator-based mechanism to simulate human consensus. |
CLOMO: Counterfactual Logical Modification with Large Language Models (2024.acl-long)
Copied to clipboard
Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song
| Challenge: | Existing studies on evaluating model reasoning are limited in both form and content. |
| Approach: | They propose a task to cultivate counterfactual thought processes within large language models and an evaluation metric to evaluate their natural language output instead of modeling the task as a multiple-choice problem. |
| Outcome: | The proposed evaluation metric aligns well with human preference. |
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis (2024.findings-emnlp)
Copied to clipboard
Jianxiang Yu, Zichen Ding, Jiaqi Tan, Kangyang Luo, Zhenmin Weng, Chenghua Gong, Long Zeng, RenJing Cui, Chengcheng Han, Qiushi Sun, Zhiyong Wu, Yunshi Lan, Xiang Li
| Challenge: | Existing approaches to review scientific papers are limited by their content or quality . SEA is a framework for automated scientific review, but its contents are generic or partial. |
| Approach: | They propose a framework for automated scientific review using large language models . they propose to use a standardized review dataset to fine-tune an LLM to generate high-quality reviews. |
| Outcome: | The proposed framework can generate high-quality reviews from standardized datasets and improves on the existing feedback mechanisms. |
OVEL: Online Video Entity Linking (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on Multi-modal Entity Linking focus on linking textual and visual mentions or offline videos’ mentions to entities in multi-modal knowledge bases. |
| Approach: | They propose a task called Online Video Entity Linking to establish connections between online videos and a knowledge base with high accuracy and timeliness. |
| Outcome: | The proposed method can establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness. |
Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to generate conversational question are naive and do not account for the answer span. |
| Approach: | They propose a framework for generating a conversational question from a context. |
| Outcome: | The proposed framework achieves state-of-the-art in two different settings compared to existing models . it uses a sentence as the rationale and extracts the answer span from it . |
Evaluating LLM-Generated Diagrams as Graphs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods on diagram generation with LLMs rely heavily on proprietary LLM systems. |
| Approach: | They propose a new evaluation metric to assess demonstration diagrams generated by large language models. |
| Outcome: | The proposed evaluation metric evaluates diagrams produced by state-of-the-art LLMs on recent research literature. |
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. |
| Approach: | They propose a lightweight method to adaptively recognize and mask untruthful context from the inputs and a new evaluation metric to further study the LLMs’ ability to accept truthful information and resist untrusted information. |
| Outcome: | The proposed method can detect and mask untruthful context from the inputs and significantly improve the quality of LLMs’ responses when presented with misleading information. |
Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics, such as ROUGE and BLEU, rely on exact word matching and fail to capture semantic similarity. |
| Approach: | They propose to use contextualized word or sentence embeddings to capture semantic similarity between sentences to evaluate text summarization methods. |
| Outcome: | The proposed evaluation metric shows that it performs faster than the current state-of-the-art on the SummEval dataset. |
Multimodal Abstractive Summarization for How2 Videos (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization is a task of producing a shorter version of the content in the document while preserving its information. |
| Approach: | They propose a new evaluation metric that measures semantic adequacy rather than fluency of abstractive summarization tasks. |
| Outcome: | The proposed model integrates information from different sources into a coherent output. |
Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing (2024.acl-long)
Copied to clipboard
| Challenge: | Recent work has proposed a new task of textless speech constituency parsing that uses textless parsers to parse spoken word boundaries over automatically recognized spoken word borders. |
| Approach: | They propose a metric that compares a constituency parse tree over spoken word boundaries with a ground-truth parser tree over written words. |
| Outcome: | The proposed metric shows higher tolerance to syntactically plausible parses than PARSEVAL. |
Using Context in Neural Machine Translation Training Objectives (2020.acl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) training is based on document-level metrics, not sentence-level BLEU. |
| Approach: | They propose to merge document-level metrics with batch-level documents to improve NMT training. |
| Outcome: | The proposed training is more robust for document-level metrics than sequence MRT and maximum-likelihood training. |
BLEURT: Learning Robust Metrics for Text Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Text generation has made significant advances, but evaluation metrics have lagged behind. |
| Approach: | They propose a learning evaluation metric for English based on BERT . BLEURT can model human judgment with a few thousand possibly biased training examples . |
| Outcome: | The proposed model can model human judgment with a few thousand potentially biased training examples. |
A State-independent and Time-evolving Network for Early Rumor Detection in Social Media (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to rumor detection ignored dynamical evolution of an event and failed to capture its unique features in different states. |
| Approach: | They propose a state-independent and time-evolving Network (STN) for rumor detection based on fine-grained event state detection and segmentation. |
| Outcome: | The proposed framework can significantly improve the rumor detection accuracy in comparison with some strong baseline systems. |
History for Visual Dialog: Do we really need it? (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that dialog-based interaction grounded in visual information is not as effective as previous VQA tasks because of its dialog history. |
| Approach: | They propose a visual dialogue subset which explicitly encodes dialog history and a NDCG benchmark of 63%. |
| Outcome: | The proposed subset (VisdialConv) of the VisdialVal set achieves state-of-the-art performance on 72 % of the data. |
Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics conflate simplicity with correlated attributes such as fluency or meaning preservation. |
| Approach: | They propose a new learning evaluation metric that focuses on simplicity outperforming most existing metrics in terms of correlation with human judgements. |
| Outcome: | The proposed metric outperforms most existing metrics in terms of correlation with human judgements. |
Wasserstein Selective Transfer Learning for Cross-domain Text Mining (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve the learning of data-scarce target domains have negative transfer due to the data distributions between source and target domain. |
| Approach: | They propose a method that uses a reinforced selector to select helpful data for transfer learning and a Wasserstein-based discriminator to maximize the distance between the selected data and target data. |
| Outcome: | The proposed method performs better on three real-world text mining tasks. |
Complex Numerical Reasoning with Numerical Semantic Pre-training Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Numerical knowledge graphs (NKGs) are not limited to discrete entity-relation knowledge. |
| Approach: | They propose to combine numerical values and entities to solve multi-hop complex reasoning over incomplete knowledge graphs. |
| Outcome: | The proposed approach handles up to 102 types of complex numerical reasoning queries on three public datasets. |
Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation (2023.acl-long)
Copied to clipboard
| Challenge: | Argument summarisation is a promising but currently under-explored field. |
| Approach: | They propose a framework to generate key points from short texts in a task known as Key Point Analysis. |
| Outcome: | The proposed framework improves state-of-the-art in argument summarisation with performance improvement of 14 percentage points compared to ROUGE and human evaluation scores. |
Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing controllable dialogue generation models focus on single attribute and lack generalization capability to out-of-distribution multiple attribute combinations. |
| Approach: | They propose a compositional generalization model that learns from seen attributes and generalizes to unseen combinations. |
| Outcome: | The proposed model can learn from seen attribute values and generalize to unseen combinations. |
TOWER: Tree Organized Weighting for Evaluating Complex Instructions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Evaluating the ability of large language models to follow human-written instructions remains a challenge. |
| Approach: | They propose a new evaluation metric that incorporates human-judged importance into the assessment of complex instruction following. |
| Outcome: | The proposed evaluation metric incorporates human-judged importance into the assessment of complex instruction following. |
MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to knowledge graph completion have not integrated the structural attributes of knowledge graphs with the textual descriptions of entities to generate robust entity encodings. |
| Approach: | They propose to integrate structural information from knowledge graphs with textual descriptions of entities to generate robust entity encodings. |
| Outcome: | The proposed model improves on the standard evaluation metric, Mean Reciprocal Rank (MRR), while surpassing the current best model on the Wikidata5M dataset. |
ASTRID - An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | Current automated RAG metrics perform poorly in clinical and conversational use cases. |
| Approach: | They propose an automated and scaleable TRIaD for evaluating clinical QA systems leveraging Retrieval Augmented Generation (RAG) metric consisting of three metrics: Context Relevance (CR), Refusal Accuracy (RA), and Conversational Faithfulness (CF). |
| Outcome: | The proposed metric captures the faithfulness of a model’s response without penalising conversational elements and captures refusal to address questions outside of the system’s scope of practice. |
CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code (2023.emnlp-main)
Copied to clipboard
| Challenge: | NLCode generates long expressions and statements rather than a single next-token . evaluating and comparing different models has remained a challenge . |
| Approach: | They propose a code-generating evaluation metric built on BERTScore . they use five language-specific pretrained models to evaluate their code . |
| Outcome: | The proposed evaluation metric achieves higher correlation with human preference and functional correctness than existing metrics across four programming languages. |
PAM: Paraphrase AMR-Centric Evaluation Metric (2025.findings-acl)
Copied to clipboard
| Challenge: | Current evaluation metrics for paraphrase generation are based on borrowed metrics from text-to-text tasks . this is not ideal for paraphrasing as we typically want variation in the lexicon while persisting semantics. |
| Approach: | They propose a Paraphrase AMR-Centric Evaluation Metric that uses AMR graphs extracted from the input text to evaluate paraphrases. |
| Outcome: | The proposed evaluation metric improves on different semantic textual similarity datasets on paraphrases with human semantic scores. |
DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies suggest that neural classifiers make overly confident predictions for examples from unseen distributions. |
| Approach: | They propose a new evaluation metric, DENSITY, which measures how likely a response would appear in the distribution of human conversations. |
| Outcome: | The proposed metric measures how likely a response would appear in the distribution of human conversations. |
Are Your LLMs Capable of Stable Reasoning? (2025.findings-acl)
Copied to clipboard
Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen
| Challenge: | Existing evaluation protocols and metrics do not capture the full spectrum of LLM capabilities, especially in complex reasoning tasks. |
| Approach: | They propose a new evaluation metric that continuously assesses model performance across multiple sampling attempts, quantifying both the model’s potential capabilities and operational consistency. |
| Outcome: | The proposed evaluation metric measures model performance across multiple sampling attempts and provides comprehensive insights into their potential capabilities and operational consistency. |
Assessing the Sensitivity and Alignment of FOL Closeness Metrics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent paradigm of logical reasoning with tool-augmented large language models has been successful, but the correctness of FOL statements often go unverified due to the lack of a reliable evaluation metric. |
| Approach: | They compare sensitivity of existing metrics and their alignment with LLM to evaluate FOLs. |
| Outcome: | The proposed metrics improve the sensitivity and robustness of the proposed models. |
Evaluating and Aligning Human Economic Risk Preferences in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. |
| Approach: | They propose an evaluation metric called Risk Disparity Score (RDS) and assess whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual’s persona. |
| Outcome: | The proposed evaluation metric assesses whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual’s persona. |
Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | n-gram-based metrics are considered indicative (even if imperfect) of human evaluation for English, but their suitability for other languages remains unclear. |
| Approach: | They systematically assess evaluation metrics for generation for languages and tasks using n-gram-based and neural-based metrics. |
| Outcome: | The proposed evaluation suite is based on eight languages from four typological families and shows that it is sensitivity to the language type at hand. |
Multi-Document Event Extraction Using Large and Small Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multi-document event extraction have limited attention . despite its practical significance, this task has inherent challenges . |
| Approach: | They propose a collaborative framework that integrates large language models for multi-step reasoning and fine-tuned small language models to handle key subtasks. |
| Outcome: | The proposed framework outperforms existing methods and provides new insights into collaborative reasoning to tackle the complexities of multi-document event extraction. |
AnCast++: Document-Level Evaluation of Graph-based Meaning Representations (2025.findings-acl)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (UMR) is a cross-lingual document-level graph-based representation that extends it to document- level semantic annotations. |
| Approach: | They propose an evaluation metric that unifies evaluation of four distinct sub-structures of UMR. |
| Outcome: | The proposed metric is made available on Github. |
Topic-Controllable Summarization: Topic-Aware Evaluation and Transformer Methods (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for topic-controllable summarization are limited by their recurrent architectures and require modifications to the model's architecture for controlling the topic. |
| Approach: | They propose a new topic-oriented evaluation measure to automatically evaluate the generated summaries based on the topic affinity between the generated summary and the desired topic. |
| Outcome: | The proposed method achieves better performance compared to more complicated embedding-based approaches while also being significantly faster. |
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)
Copied to clipboard
Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang
| Challenge: | Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers. |
| Approach: | They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification. |
| Outcome: | The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification. |
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)
Copied to clipboard
Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun
| Challenge: | Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities. |
| Approach: | They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts. |
| Outcome: | The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs. |
Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss (2025.emnlp-main)
Copied to clipboard
Kiana Aghakasiri, Noopur Zambare, JoAnn Thai, Carrie Ye, Mayur Mehta, J Ross Mitchell, Mohamed Abdalla
| Challenge: | De-identification is an application of NLP where automated algorithms remove identifying information of patients and providers. |
| Approach: | They propose to use generative large language models to de-identify patients and providers . they propose to validate existing metrics to quantify extent of inappropriate removal . |
| Outcome: | The proposed method is based on a survey of LLM-based de-identification research . it shows that the models perform poorly in identifying clinically relevant changes . |
Prompt Optimization for Relation Extraction using Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based methods rely heavily on large-scale annotated datasets limiting their applicability in domain-specific and low-resource scenarios. |
| Approach: | They propose a reinforcement learning-based automated prompt optimization framework for domain relation extraction that optimizes prompt quality through interaction with a black-box LLM. |
| Outcome: | The proposed framework outperforms existing prompt-based methods and supervised baselines on multiple extraction datasets across medical, financial, legal, and news domains. |
MedQPA-Gen: Medical Question Proposing and Answering for Report Generation (2026.findings-acl)
Copied to clipboard
Weijie Liang, Xiyue Zhu, Ruike Zhu, Chenhao Li, Cheng Tang, Zhiyu Liu, Zhihua Gong, Shirui Luo, Yudu Li, Volodymyr Kindratenko
| Challenge: | Existing training paradigms fail to explicitly target factual accuracy, resulting in inaccuracies and serious patient safety risks. |
| Approach: | They propose an automatic and generalizable report evaluation technique that uses question proposing and answering to enable controllable, structured reasoning grounded in medical domain knowledge and the factual correctness of the report. |
| Outcome: | The proposed method can improve human preference scores and perform better on downstream tasks. |