Austria

This paper introduces the new and challenging TempVS benchmark, which focuses on temporal grounding and reasoning capabilities of Multimodal Large Language Models (MLLMs) in image sequences. TempVS consists of three main tests (i.e., event relation inference, sentence ordering and image ordering) and each accompanied with a basic grounding test, yielding a total of 2,085 annotated image sequences and 15k multiple-choice questions. TempVS requires MLLMs to rely on both visual and linguistic modalities to understand the temporal order of events. We extensively evaluate 38 state-of-the-art MLLMs, demonstrating that models struggle to solve TempVS. Our analysis reveals a substantial performance gap between current MLLMs and human capabilities, accompanied by fine-grained insights that suggest promising directions for future research.

ACL 2025

Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?

temporal understanding and reasoning

multimodal large language models

vision and language

### 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)

poster

While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of whether the user revealed their identity intentionally through explicit indications or unintentionally through implicit cues. We demonstrate that when people use large language models (LLMs) to generate recommendations, the LLMs produce responses that reflect both what the user wants and who the user is. We argue that chatbots ought to transparently indicate when recommendations are influenced by a user’s revealed identity characteristics, but observe that they currently fail to do so. Our experiments show that even though a user’s revealed identity significantly influences model recommendations ($p < 0.001$), model responses obfuscate this fact in response to user queries. This bias and lack of transparency occurs consistently across multiple popular consumer LLMs and for four American racial groups.

Stereotype or Personalization? User Identity Biases Chatbot Recommendations

While a few high-quality bias benchmark datasets exist to address stereotypes in Language Models (LMs), a notable lack of focus remains on body image stereotypes. To bridge this gap, we propose BIStereo, a suite to uncover LMs’ biases towards people of certain physical appearance characteristics, namely, skin complexion, body shape, height, attire, and a miscellaneous category including hair texture, eye color, and more. Our dataset comprises 40k sentence pairs designed to assess LMs’ biased preference for certain body types. We further include 60k premise-hypothesis pairs designed to comprehensively assess LMs’ preference for fair skin tone. Additionally, we curate 553 tuples consisting of a body image descriptor, gender, and a stereotypical attribute, validated by a diverse pool of annotators for physical appearance stereotypes.We propose a metric, TriSentBias, that captures the biased preferences of LMs towards a certain body type over others. Using BIStereo, we assess the presence of body image biases in ten different language models, revealing significant biases in models Muril, XLMR, Llama3, and Gemma. We further evaluate the LMs through downstream NLI and Analogy tasks.Our NLI experiments highlight notable patterns in the LMs that align with the well-documented cognitive bias in humans known as the Halo Effect.

“You are Beautiful, Body Image Stereotypes are Ugly!” BIStereo: A Benchmark to Measure Body Image Stereotypes in Language Models

Large Language Models (LLMs) exhibit sophisticated reasoning yet still generate incorrect answers. We attribute these errors to **Spurious Beliefs**, defined as propositions the model internally considers as true despite being factually false. 

To reduce reasoning errors, we propose a belief space rectification framework. Our method first identifies the beliefs invoked during inference via an explanation‑based approach with Forward‑Backward Beam Search (FBBS). We subsequently apply unlearning via gradient ascent to suppress spurious beliefs and enhance true ones, thereby effectively rectifying the model’s belief space. 

Experiments on three QA datasets and three LLMs show that our method significantly reduces erroneous reasoning and improves generalization.

Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning

Accurately grounding visual and textual elements within mobile user interfaces (UIs) remains a significant challenge for Vision-Language Models (VLMs). Visual grounding, a critical task in this domain, involves identifying the most relevant UI element or region based on a natural language query—a process that requires both precise perception and context-aware reasoning. In this work, we present - **MoUI**, a light-weight mobile UI understanding model trained on **MoIT**, an instruction-tuning dataset specifically tailored for mobile screen understanding and grounding, designed to bridge the gap between user intent and visual semantics. Complementing this dataset, we also present a human-annotated reasoning benchmark **MoIQ** that rigorously evaluates complex inference capabilities over mobile UIs. To harness these resources effectively, we propose a two-stage training approach that separately addresses perception and reasoning tasks, leading to stronger perception capabilities and improvement in reasoning abilities. Through extensive experiments, we demonstrate that our MoUI models achieve significant gains in accuracy across all perception tasks and _state-of-the-art_ results on public reasoning benchmark **ComplexQA (78%) and our MoIQ (49%)**. We will be open-sourcing our dataset, code, and models to foster further research and innovation in the field.

From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding

Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation. Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure. Our experiments with GPT2 and Llama3-8B models show that with an appropriate proposal distribution, we can improve syntactic accuracy, increasing the F1 score from 12.31 (GPT2-large) and 35.33 (Llama3-8B) to about 93 in both cases without compromising the language model's fluency. These results underscore both the complexity of syntactic control and the effectiveness of sampling algorithms, offering a promising approach for applications where precise control over syntax is essential.

Syntactic Control of Language Models by Posterior Inference

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap: small models (
3B parameters) do not consistently benefit from long chain-of-thought (CoT) reasoning or distillation from larger models. Instead, they perform better when fine-tuned on shorter, simpler reasoning chains that better align with their intrinsic learning capacity. To address this, we propose Mix Distillation, a simple yet effective strategy that balances reasoning complexity by combining long and short CoT examples or reasoning from both larger and smaller models. Our experiments demonstrate that Mix Distillation significantly improves small model reasoning performance compared to training on either data alone. These findings highlight the limitations of direct strong model distillation and underscore the importance of adapting reasoning complexity for effective reasoning capability transfer.

Small Models Struggle to Learn from Strong Reasoners

Cross-lingual vocabulary transfer plays a promising role in adapting pre-trained language models to new languages, including low-resource languages. Existing approaches that utilize monolingual or parallel corpora face challenges when applied to languages with limited resources. In this work, we propose a simple yet effective vocabulary transfer method that utilizes bilingual dictionaries, which are available for many languages, thanks to descriptive linguists. Our proposed method leverages a property of BPE tokenizers where removing a subword from the vocabulary causes a fallback to shorter subwords. The embeddings of target subwords are estimated iteratively by progressively removing them from the tokenizer. The experimental results show that our approach outperforms existing methods for low-resource languages, demonstrating the effectiveness of a dictionary-based approach for cross-lingual vocabulary transfer.

Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries

Recent Large Language Models (LLMs) have demonstrated impressive translation performance without requiring fine-tuning on additional parallel corpora. However, they still face significant challenges in certain scenarios, particularly when translating low-resource languages. A common approach to address this issue is to provide external knowledge, such as few-shot examples, to assist LLMs in translating specific source sentences. However, this method is fundamentally limited by the quality or quantity of relevant sources, which cannot always be guaranteed. To reduce LLMs' reliance on external sources, we propose BridG MT, a method that combines Sentence Bridging, which generates a sequence of sentences as a bridge that gradually transition from easy-to-translate to more difficult, and Gradual MT, which sequentially translates these sentences using earlier translations as few-shot examples for subsequent ones. Experiments conducted on four LLMs across seven languages demonstrate that our method effectively enhances translation performance, achieving results that cannot be attained by simply providing a large number of few-shot examples.

BridG MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Bridging and Gradual MT

This study investigates the halo effect in AI-driven hiring evaluations using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Through experiments with hypothetical job applications, we examined how these models' evaluations are influenced by non-job-related information including extracurricular activities, social media images, and video interview backgrounds. By analyzing models' responses to Likert-scale questions across different competency dimensions, we found that AI models exhibit significant halo effects, particularly in image-based evaluations, while text-based assessments showed more resistance to bias. The findings demonstrate that supplementary multimodal information can substantially influence AI hiring decisions, highlighting potential risks in AI-based recruitment systems.

Shiny Inputs, Shiny Outputs? Unveiling the Halo Effect in MultiModal LLMs

Existing fairness benchmarks for large language models (LLMs) primarily focus on simple tasks, such as multiple-choice questions, overlooking biases that may arise in more complex scenarios like long-text generation. To address this gap, we introduce the Long Text Fairness Test (LTF-TEST), a framework that evaluates biases in LLMs through essay-style prompts. LTF-TEST covers 14 topics and 10 demographic axes, including gender and race, resulting in 11,948 samples. By assessing both model responses and the reasoning behind them, LTF-TEST uncovers subtle biases that are difficult to detect in simple responses. In our evaluation of five recent LLMs, including GPT-4o and LLaMA3, we identify two key patterns of bias. First, these models frequently favor certain demographic groups in their responses. Second, they show excessive sensitivity toward traditionally disadvantaged groups, often providing overly protective responses while neglecting others. To mitigate these biases, we propose REGARD-FT, a finetuning approach that pairs biased prompts with neutral responses. REGARD-FT reduces gender bias by 34.6% and improves performance by 1.4 percentage points on the BBQ benchmark, offering a promising approach to addressing biases in long-text generation tasks.

Downloads

Next from ACL 2025

Stereotype or Personalization? User Identity Biases Chatbot Recommendations

Similar lecture

Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?