Austria

Large language models (LLMs) now achieve near-human performance on standard math word problem benchmarks (e.g., GSM8K), yet their true reasoning ability remains disputed. A key concern is that models often produce confident, yet unfounded, answers to unanswerable problems. We introduce TreeCut, a synthetic dataset that systematically generates infinite unanswerable math word problems and their answerable counterparts, by representing each question as a tree and removing chosen necessary conditions. Experiments show TreeCut effectively induce hallucinations in large language models, including GPT-4o and o3-mini, with rates of 64% and 44% in their respective worst-case scenarios under zero-shot setting. Further analysis highlights that deeper or more complex trees, composite item names, and removing necessary condition near the middle of a path all increase the likelihood of hallucinations, underscoring the persistent challenges LLMs face in identifying unanswerable math problems. The dataset generation code and sample data are available at \url{https://github.com/j-bagel/treecut-math}.

ACL 2025

TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation

mathematical nlp

math qa

evaluation

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

technical paper

Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded tasks and hallucinations. We hypothesize that this issue arises because existing VLMs are not explicitly trained to generate texts that are accurately grounded in fine-grained image details. To enhance visual feedback during VLM training, we propose S-VCO (Symmetrical Visual Contrastive Optimization), a novel finetuning objective that steers the model toward capturing important visual details and aligning them with corresponding text tokens. To further facilitate this detailed alignment, we introduce MVC, a paired image-text dataset built by automatically filtering and augmenting visual counterfactual data to challenge the model with hard contrastive cases involving Minimal Visual Contrasts. Experiments show that our method consistently improves VLM performance across diverse benchmarks covering various abilities and domains, achieving up to a 22% reduction in hallucinations, and significant gains in vision-centric and general tasks. Notably, these improvements become increasingly pronounced in benchmarks with higher visual dependency. In short, S-VCO offers a significant enhancement of VLM's visually-dependent task performance while retaining or even improving the model's general abilities.

Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images

Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied. We present an embodied emotion classification dataset, CHEER-Ekman, extending the existing binary embodied emotion dataset with Ekman's six basic emotion categories. Using automatic best-worst scaling with large language models, we achieve performance superior to supervised approaches on our new dataset. Our investigation reveals that simplified prompting instructions and chain-of-thought reasoning significantly improve emotion recognition accuracy, enabling smaller models to achieve competitive performance with larger ones.

CHEER-Ekman: Fine-grained Embodied Emotion Classification

Fairness in multi-document summarization (MDS) is crucial for providing comprehensive views across documents with diverse social attribute values, which can significantly impact decision-making. For example, a summarization system that tends to overrepresent negative reviews of products can mislead customers into disregarding good products. Previous works measure fairness in MDS at two levels: summary-level and corpus-level. While summary-level fairness focuses on individual summaries, corpus-level fairness focuses on a corpus of summaries. Recent methods primarily focus on summary-level fairness. We propose FairPO, a preference tuning method that focuses on both summary-level and corpus-level fairness in MDS. To improve summary-level fairness, we propose to generate preference pairs by perturbing document sets. To improve corpus-level fairness, we propose fairness-aware preference tuning by dynamically adjusting the weights of preference pairs. Our experiments show that FairPO outperforms strong baselines while maintaining the critical qualities of summaries. The code is available at https://github.com/leehaoyuan/coverage_fairness

Improving Fairness of Large Language Models in Multi-document Summarization

Although weight quantization helps large language models (LLMs) in resource-constrained environments, its influence on the uncertainty calibration remains unexplored. To bridge this gap, we presents a comprehensive investigation of uncertainty calibration for quantized LLMs in this work. Specifically, we propose an analytic method to estimate the upper bound of calibration error (UBCE) for LLMs. Our method separately discusses the calibration error of the model's correct and incorrect predictions, indicating a theoretical improvement of calibration error caused by the weight quantization. Our study demonstrates that quantized models consistently exhibit worse calibration performance than full-precision models, supported by consistent analysis across multiple LLMs and datasets. To address the calibration issues of quantized models, we propose a novel method of post calibration for recovering the calibration performance of quantized models through soft-prompt tuning. Specifically, we inject soft tokens to quantized models after the embedding layers, and optimize these tokens to recover the calibration error caused by the weight quantization. Experimental results on multiple datasets demonstrate our effectiveness in improving the uncertainty calibration of quantized LLMs, facilitating more reliable weight quantization in resource-constrained environments.

Quantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language Models

Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even malicious information. Previous studies have rarely connected the behavior of RAG through joint analysis, particularly regarding error propagation coming from imperfect retrieval and potential conflicts between LLMs' internal knowledge and external sources. Through comprehensive and controlled analyses under realistic conditions, we find that imperfect retrieval augmentation is inevitable, common, and harmful. We identify the knowledge conflicts between LLM-internal and external knowledge from retrieval as a bottleneck to overcome imperfect retrieval in the post-retrieval stage of RAG. To address this, we propose Astute RAG, a novel RAG approach designed to be resilient to imperfect retrieval augmentation. It adaptively elicits essential information from LLMs' internal knowledge, iteratively consolidates internal and external knowledge with source-awareness, and finalizes the answer according to information reliability. Our experiments with Gemini and Claude demonstrate the superior performance of Astute RAG compared to previous robustness-enhanced RAG approaches. Specifically, Astute RAG is the only RAG method that achieves performance comparable to or even surpassing conventional use of LLMs under the worst-case scenario. Further analysis reveals the effectiveness of Astute RAG in resolving knowledge conflicts, thereby improving the trustworthiness of RAG.

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Recently, GraphRAG systems have achieved remarkable progress in enhancing the performance and reliability of large language models (LLMs). However, most previous benchmarks are template-based and primarily focus on few-entity queries, which are monotypic and simplistic, failing to offer comprehensive and robust assessments. Besides, the lack of ground-truth reasoning paths also hinders the assessments of different components in GraphRAG systems. To address these limitations, we propose $\text{M}^3\text{GQA}$, a complex, diverse, and high-quality GraphRAG benchmark focusing on multi-entity queries, with six distinct settings for comprehensive evaluation. In order to construct diverse data with semantically correct ground-truth reasoning paths, we introduce a novel reasoning-driven four-step data construction method, including tree sampling, reasoning path backtracking, query creation, and multi-stage refinement and filtering. Extensive experiments demonstrate that $\text{M}^3\text{GQA}$ effectively reflects the capabilities of GraphRAG methods, offering valuable insights into the model performance and reliability. By pushing the boundaries of current methods, $\text{M}^3\text{GQA}$ establishes a comprehensive, robust, and reliable benchmark for advancing GraphRAG research.

M3GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering Benchmark

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms.
However, existing PAVI methods face critical challenges, such as inferring implicit values, handling out-of-distribution (OOD) values, and producing normalized outputs.
To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI.
TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference with dynamic thresholds.
TACLR offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial deployment.
Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Further, it has been successfully deployed on the real-world e-commerce platform Xianyu, processing millions of product listings daily with frequently updated, large-scale attribute taxonomies. 
We release the code to facilitate reproducibility and future research at https://github.com/SuYindu/TACLR.

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification

Fact-checking tabular data is essential for ensuring the accuracy of structured information in domains such as journalism, finance, and scientific research. However, existing methods often rely on black-box models with opaque reasoning. We introduce RePanda, a structured fact verification approach that translates claims into executable pandas queries, enabling interpretable and verifiable reasoning.

To train RePanda, we construct PanTabFact, a structured dataset derived from TabFact, where claims are paired with executable queries generated using DeepSeek-Chat and refined through automated error correction. Fine-tuning DeepSeek-coder-7B-instruct-v1.5 on PanTabFact, RePanda achieves 84.09% accuracy on TabFact. To assess Out-of-Distribution (OOD) generalization, we create a dataset named WikiFact from WikiTableQuestions by transforming question-answer pairs into factual claims. Without additional fine-tuning, RePanda achieves 84.72% accuracy on WikiFact, significantly outperforming all other baselines and demonstrating strong OOD robustness. PanTabFact is publically available on HuggingFace at datasets/AtoosaChegini/PanTabFact.

Beyond fact verification, RePanda extends to tabular question answering by generating executable queries that retrieve precise answers. To support this, we introduce PanWiki, a dataset mapping WikiTableQuestions to pandas queries. Fine-tuning on PanWiki, RePanda achieves 75.1% accuracy in direct answer retrieval. These results highlight the effectiveness of structured execution-based reasoning for tabular verification and question answering.

RePanda: Pandas-powered Tabular Verification and Reasoning

Low-bit quantization improves machine learning model efficiency but surprisingly favors undertrained large language models (LLMs). Larger models or those trained on fewer tokens exhibit less quantization-induced degradation (QiD), while smaller, well-trained models face significant performance losses. To gain deeper insights into this trend, we study over 1500+ quantized LLM checkpoints of various sizes and at different training levels (undertrained or fully trained) in a controlled setting, deriving scaling laws for understanding the relationship between QiD and factors: the number of training tokens, model size and bit width.

With our derived scaling laws, we propose a novel perspective that we can use QiD to measure an LLM's training levels and determine the number of training tokens required for fully training LLMs of various sizes. Moreover, we use the scaling laws to predict the quantization performance of different-sized LLMs trained with tokens. Our projection shows that the low-bit quantization performance of future models, which are expected to be trained with over $\textcolor{red}{100~trillion}$ tokens, may NOT be desirable. This poses a potential challenge for low-bit quantization in the future and highlights the need for awareness of a model's training level when evaluating low-bit quantization research. To facilitate future research on this problem, we release all the 1500+ quantized checkpoints used in this work at https://huggingface.co/Xu-Ouyang.

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens

As large language models (LLMs) scale in size and adoption, their computational and environmental costs continue to rise. Prior benchmarking efforts have primarily focused on latency reduction in idealized settings, often overlooking the diverse real-world inference workloads that shape energy use. In this work, we systematically analyze the energy implications of common inference efficiency optimizations across diverse Natural Language Processing (NLP) and generative Artificial Intelligence (AI) workloads, including conversational AI and code generation. 
We introduce a modeling approach that approximates real-world LLM workflows through a binning strategy for input-output token distributions and batch size variations. Our empirical analysis spans software frameworks, decoding strategies, GPU architectures, online and offline serving settings, and model parallelism configurations. 
We show that the effectiveness of inference optimizations is *highly sensitive to workload geometry, software stack, and hardware accelerators*, demonstrating that naive energy estimates based on FLOPs or theoretical GPU utilization significantly underestimate real-world energy consumption.
Our findings reveal that the proper application of relevant inference efficiency optimizations can reduce total energy use by up to **73%** from unoptimized baselines. These insights provide a foundation for sustainable LLM deployment and inform energy-efficient design strategies for future AI infrastructure.

Downloads

Next from ACL 2025

Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images

Similar lecture

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes