China

Commonsense visual–question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLMs respectively across two commonsense VQA datasets (CRIC, AOKVQA) and a visual-entailment dataset (e-SNLI-VE). Facts retrieved using a fine-tuned ColBERTv2 and an object information-enriched prompt yield explanations that largely cut down hallucinations, while lifting the end-to-end answer accuracy by up to 7 pts (across 3 datasets), making FLAVA and other models in NLKI match or exceed medium-sized VLMs such as Qwen-2 VL-2B and SmolVLM-2B. As these benchmarks contain 10–25% label noise, additional finetuning using noise-robust losses (such as symmetric cross entropy and generalised cross entropy) gains another 2.5 (in CRIC, to 5.5 in AOKVQA).

EMNLP 2025

NLKI: A Lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

vision

reasoning

commonsense

### 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**. 

ACL 2025

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

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Large Language Models (LLMs) and their multimodal variations can now accept visual inputs, including images of text, raising an intriguing possibility: can we compress textual inputs by feeding them as images to reduce token usage while preserving performance? In this paper, we show that visual text representations are a practical and surprisingly effective form of input compression for LLMs. Using visual input in place of long text, multimodal models can achieve comparable reasoning performance at significantly reduced input token cost. We demonstrate this on a challenging reasoning benchmark (BABILong~1k), where a state-of-the-art vision-language model (Gemini-2.5) attains higher accuracy than GPT-4.1 with up to 50% fewer tokens. We analyze when this approach succeeds and discuss the trade-offs of image vs.\ text inputs, highlighting a new avenue for improving LLM scalability and cost-efficiency in real-world deployments.

Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs

Aligning large language models (LLMs) with specific task objectives is challenging, especially when access to feedback signals for guiding the model is limited. While existing parametric methods perform reasonably, they rely heavily on large datasets and frequent feedback, making them impractical in scenarios with limited human feedback. We introduce Alignment Learning with Episodic Control (ALEC), a non-parametric framework that aligns LLM outputs during inference without fine-tuning. ALEC employs a key-value memory to store the associations between generated text and its corresponding values. It leverages a novel confidence-based writing scheme to update these stored values, maximizing the use of available data. During inference, ALEC utilizes a nearest-neighbor mechanism to estimate the values of generated texts, enabling the selection of the optimal text for decoding. Our method outperforms state-of-the-art baselines on harmless, helpful, and summarization tasks, demonstrating improved alignment with minimal interactions with the true reward model.

Sample Efficient Alignment Learning With Episodic Control

Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures. We propose Geometric Distillation, a lightweight, annotation-free fine-tuning framework that injects human-inspired geometric cues into pretrained VLMs without modifying their architecture. By distilling (1) sparse correspondences, (2) relative depth relations, and (3) dense cost volumes from off-the-shelf 3D foundation models (e.g., MASt3R, VGGT), our method shapes representations to be geometry-aware while remaining compatible with natural image–text inputs. Through extensive evaluations on 3D vision-language reasoning and 3D perception benchmarks, our method consistently outperforms prior approaches, achieving improved 3D spatial reasoning with significantly lower computational cost. Our work demonstrates a scalable and efficient path to bridge 2D-trained VLMs with 3D understanding, opening up wider use in spatially grounded multimodal tasks.

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome this, we introduce textbfAgentThink, a pioneering unified framework that, for the first time, integrates Chain-of-Thought (CoT) reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. AgentThink's core innovations include: textbf(i) Structured Data Generation, by establishing an autonomous driving tool library to automatically construct structured, self-verified reasoning data explicitly incorporating tool usage for diverse driving scenarios; textbf(ii) A Two-stage Training Pipeline, employing Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to equip VLMs with the capability for autonomous tool invocation; and textbf(iii) Agent-style Tool-Usage Evaluation, introducing a novel multi-tool assessment protocol to rigorously evaluate the model's tool invocation and utilization. Experiments on the DriveLMM-o1 benchmark demonstrate AgentThink significantly boosts overall reasoning scores by textbf53.91\% and enhances answer accuracy by textbf33.54\%, while markedly improving reasoning quality and consistency. Furthermore, ablation studies and robust zero-shot/few-shot generalization experiments across various benchmarks underscore its powerful capabilities. These findings highlight a promising trajectory for developing trustworthy and tool-aware autonomous driving models.

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving

Chart understanding requires models to effectively analyze and reason about numerical data, textual elements, and complex visual components. Our observations reveal that the perception capabilities of existing large vision-language models (LVLMs) constitute a critical bottleneck in this process. In this study, we delve into this perception bottleneck by decomposing it into two components: the vision encoder bottleneck, where the visual representation may fail to encapsulate the correct information, and the extraction bottleneck, where the language model struggles to extract the necessary information from the provided visual representations. Through comprehensive experiments, we find that (1) the information embedded within visual representations is substantially richer than what is typically captured by linear extractors, such as the widely used retrieval accuracy metric; (2) While instruction tuning effectively enhances the extraction capability of LVLMs, the vision encoder remains a critical bottleneck, demanding focused attention and improvement. Therefore, we further enhance the visual encoder to mitigate the vision encoder bottleneck under a contrastive learning framework. Empirical results demonstrate that our approach significantly mitigates the perception bottleneck and improves the ability of LVLMs to comprehend charts.

On the Perception Bottleneck of VLMs for Chart Understanding

Generative Information Retrieval is an emerging retrieval paradigm that exhibits remarkable performance in monolingual scenarios. However, applying these methods to multilingual retrieval still encounters two primary challenges, cross-lingual identifier misalignment and identifier inflation. To address these limitations, we propose Multilingual Generative Retrieval via Cross-lingual Semantic Compression (MGR-CSC), a novel framework that unifies semantically equivalent multilingual keywords into shared atoms to align semantics and compresses the identifier space, and we propose a dynamic multi-step constrained decoding strategy during retrieval. MGR-CSC improves cross-lingual alignment by assigning consistent identifiers and enhances decoding efficiency by reducing redundancy. Experiments demonstrate that MGR-CSC achieves outstanding retrieval accuracy, improving by 6.83% on mMarco100k and 5.01% on mNQ320k, while reducing document identifiers length by 74.51% and 78.2%, respectively. We publicly release our dataset and code at https://anonymous.4open.science/r/MGR-CSC-D01C

Multilingual Generative Retrieval via Cross-lingual Semantic Compression

Lexical semantic change has been investigated extensively through corpus studies across many languages, but its underlying principles remain hard to unravel through experimental paradigms due to their extended diachronic processes. This work introduces NeLLCom-Lex, a neural-agent framework to simulate semantic change by first grounding agents in a real lexical system (e.g. English) and then systematically manipulating their communicative needs. We use a well-established color naming task to study which factors lead agents to modulate their naming choices according to the situational context and maintain efficient and understandable lexical systems. Our experiments with different supervised and reinforcement learning pipelines show that neural agents trained to `speak' an existing language can reproduce human-like patterns in color naming, supporting their use for simulating and explaining semantic change in real lexical systems.

NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use

Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource languages due to resource constraints, which struggles with multilingual reasoning tasks. To this end, we propose Structured-of-Thought (SoT), a training-free method that improves the performance on multilingual reasoning through a multi-step transformation: Language Thinking Transformation and Structured Knowledge Transformation. The SoT method converts language-specific semantic information into language-agnostic structured representations, enabling the models to understand the query in different languages more sophisticated. Besides, SoT effectively guides LLMs toward more concentrated reasoning to maintain consistent underlying reasoning pathways when handling cross-lingual variations in expression. Experimental results demonstrate that SoT outperforms several strong baselines on multiple multilingual reasoning benchmarks when adapting to various backbones of LLMs. It can also be integrated with other training-free strategies for further improvements. Our code is available at https://anonymous.4open.science/r/SoT-E461/.

SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models

The advancement of Large Language Models (LLMs) enables flexible and interpretable automatic evaluations. In the field of machine translation evaluation, utilizing LLMs with translation error annotations based on Multidimensional Quality Metrics (MQM) yields more human-aligned judgments. However, current LLM-based evaluation methods still face challenges in accurately identifying error spans and assessing their severity. In this paper, we propose HiMATE, a Hierarchical Multi-Agent Framework for Machine Translation Evaluation. We argue that existing approaches inadequately exploit the fine-grained structural and semantic information within the MQM hierarchy. To address this, we develop a hierarchical multi-agent system grounded in the MQM error typology, enabling granular evaluation of subtype errors. Two key strategies are incorporated to further mitigate systemic hallucinations within the framework: the utilization of the model's self-reflective capability and the facilitation of agent discussion involving asymmetric information. Empirically, HiMATE outperforms competitive baselines across different datasets in conducting human-aligned evaluations. Further analyses underscore its significant advantage in error span detection and severity assessment, achieving an average F1-score improvement of 89% over the best-performing baseline. We make our code and data publicly available at https://anonymous.4open.science/r/HiMATE-Anony.

HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation

Children learn how to speak with a low amount of data and can be taught new words on a few-shot basis, which makes them particularly data-efficient learners. The BabyLM challenge aims at exploring language model (LM) training in the low data regime but uses metrics that concentrate on the head of the word distribution. Here, we introduce LongTail-Swap (LT-Swap), a benchmark that focuses on the tail of the distribution, i.e., measures the ability of LMs to learn new words with very little exposure, like infants do. LT-Swap is a pretraining corpus-specific test-set of acceptable versus unacceptable sentence pairs that isolate semantic and syntactic usage of rare words. Models are evaluated in a zero-shot fashion by computing the average log probabilities over the two members of each pair. We build two such test sets associated with the 10M words and 100M words BabyLM training sets respectively and evaluate 16 models from the BabyLM leaderboard. Our results show that: 1) model performances on LT-Swap exhibit sharp declines for rare words, 2) differences across models are more visible on rare words than on frequent words, and 3) increasing training data size while fixing the number of parameters improves performance for rare words. Finally, we also demonstrate that simple RAG-like methods can enhance rare word understanding, highlighting in-context learning capabilities even in small LMs. These findings underscore the importance of evaluating language models on the long tail of lexical distribution and open new directions for improving their robustness to rare linguistic phenomena. We open source the code that automatically build new instances of LT-Swap over other training datasets

Downloads

Next from EMNLP 2025

Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs

Similar lecture

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES