Austria

Current benchmarks for large language model (LLM) reasoning predominantly focus on mathematical and coding abilities, leaving a gap in evaluating broader reasoning proficiencies. One particular exception is the BIG-Bench dataset, which has served as a crucial benchmark for evaluating the general reasoning capabilities of LLMs, thanks to its diverse set of challenging tasks that allowed for a comprehensive assessment of general reasoning across various skills within a unified framework. However, recent advances in LLMs have led to saturation on BIG-Bench, and its harder version BIG-Bench Hard (BBH). State-of-the-art models achieve near-perfect scores on many tasks in BBH, thus diminishing its utility. To address this limitation, we introduce BIG-Bench Extra Hard (BBEH), a new benchmark designed to push the boundaries of LLM reasoning evaluation. BBEH replaces each task in BBH with a novel task that probes a similar reasoning capability but exhibits significantly increased difficulty. We evaluate various general-purpose and reasoning-specialized models on BBEH and observe an accuracy of 23.9% for the best general-purpose model and 54.2% for the best reasoning-specialized model, indicating substantial room for improvement and highlighting the ongoing challenge of achieving robust general reasoning in LLMs. We release BBEH publicly at: https:
//github.com/google-deepmind/bbeh.

ACL 2025

BIG-Bench Extra Hard

reasoning

evaluation

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

poster

### 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)

The development of Large Language Models (LLMs) remains heavily skewed towards English and a few other high-resource languages. This linguistic disparity is particularly evident for Bangla - the 5th most spoken language. A few initiatives attempted to create open-source Bangla LLMs with performance still behind high-resource languages and limited reproducibility. To address this gap, we introduce TigerLLM - a family of Bangla LLMs. Our results demonstrate that these models surpass all open-source alternatives and also outperform larger proprietary models like GPT3.5 across standard benchmarks, establishing TigerLLM as the new baseline for future Bangla language modeling.

TigerLLM - A Family of Bangla Large Language Models

Large language models (LLMs) are increasingly used across research and industry applications, yet their inference efficiency remains a significant challenge. As the computational power of modern GPU architectures continuously improves, their memory bandwidth and capacity have not scaled proportionally, creating a critical bottleneck during inference. To address this, we investigate ternary language models (TriLMs) that employ quantization-aware training to significantly reduce memory requirements. We first analyze the scalability of TriLMs by conducting a scaling law analysis, revealing that TriLMs benefit more from increasing training data than from scaling model parameters. Based on this observation, we introduce TriTera, an open suite of TriLMs trained on up to 1.2 trillion tokens, demonstrating sustained performance gains at scale. Furthermore, to improve inference efficiency, we propose novel 2-bit and 1.6-bit packing schemes for ternary weights, which demonstrate accelerated inference across various CPU architectures. Building on the 2-bit packing, we develop a GPU kernel called TriRun that accelerates end-to-end model inference by up to 5 $\times$ compared to floating-point baselines. To encourage further exploration and development of TriLMs, we will release the TriTera suite and TriRun inference kernels. Overall, our work lays the foundation for building and deploying efficient LLMs, providing a valuable resource for the research community.

Scaling Laws and Efficient Inference for Ternary Language Models

Table-to-text generation aims to automatically produce natural language descriptions from structured or semi-structured tabular data. Unlike traditional text generation tasks, it requires models to accurately understand and represent table structures. Existing approaches typically process tables by linearizing them or converting them into graph structures. However, these methods either fail to adequately capture the table structure or rely on complex attention mechanisms, limiting their applicability. To tackle these challenges, we propose QuASAR, a question-driven self-supervised approach designed to enhance the model's structural perception and representation capabilities. Specifically, QuASAR formulates a set of structure-related queries for self-supervised training, explicitly guiding the model to capture both local and global table structures. Additionally, we introduce two auxiliary pre-training tasks: a word-to-sentence reconstruction task and a numerical summarization task, which further enhance the fluency and factuality of the generated text. Experimental results on the ToTTo and HiTab datasets demonstrate that our approach produces higher-quality text compared to existing methods.

QuASAR: A Question-Driven Structure-Aware Approach for Table-to-Text Generation

Aligning large VLMs with human preferences is a challenging task, as methods like RLHF and DPO often overfit to textual information or exacerbate hallucinations. Although augmenting negative image samples partially addresses these pitfalls, no prior work has employed listwise preference optimization for VLMs, due to the complexity and cost of constructing listwise image samples. In this work, we propose LPOI, the first object-aware listwise preference optimization developed for reducing hallucinations in VLMs. LPOI identifies and masks a critical object in the image, and then interpolates the masked region between the positive and negative images to form a sequence of incrementally more complete images. The model is trained to rank these images in ascending order of object visibility, effectively reducing hallucinations while retaining visual fidelity. LPOI requires no extra annotations beyond standard pairwise preference data, as it automatically constructs the ranked lists through object masking and interpolation. Comprehensive experiments on MMHalBench, AMBER, and Object HalBench confirm that LPOI outperforms existing preference optimization methods in reducing hallucinations and enhancing VLM performance.

LPOI: Listwise Preference Optimization for Vision Language Models

Visual perspective-taking, an ability to envision others' perspectives from a single self-perspective, is vital in human-robot interactions. Thus, we introduce a human-centric visual grounding task and a dataset to evaluate this ability. Recent advances in vision-language models (VLMs) have shown potential for inferring others' perspectives, yet are insensitive to information differences induced by slight perspective changes. To address this problem, we propose a top-view enhanced perspective transformation (TEP) method, which decomposes the transition from robot to human perspectives through an abstract top-view representation. It unifies perspectives and facilitates the capture of information differences from diverse perspectives. Experimental results show that TEP improves performance by up to 18%, exhibits perspective-taking abilities across various perspectives, and generalizes effectively to robotic and dynamic scenarios.

Walk in Others' Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation

Large vision-language models (LVLMs) perform outstandingly across various multimodal tasks. However, their ability to evaluate generated content remains limited, and training vision-language reward models (VLRMs) with preference data is computationally expensive. This paper explores a training-free alternative by merging text-based reward models (RMs) with LVLMs to create VLRMs. Our approach shows that integrating these models leads to improved performance over LVLMs' scoring and text-based RMs, offering an efficient method for incorporating textual preferences into LVLMs.

Transferring Textual Preferences to Vision-Language Understanding through Model Merging

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further misleading refinement and leading to the failure of self-correction, especially in complex reasoning tasks. In this paper, we propose Program-driven Self-Correction (ProgCo). First, program-driven verification (ProgVe) achieves complex verification logic and extensive validation through self-generated, self-executing verification pseudo-programs. Then,program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks. Experiments on three instruction-following and mathematical benchmarks indicate that ProgCo achieves effective self-correction, and can be further enhance performance when combined with real program tools. We release our code at https://github.com/songxiaoshuai/progco.

ProgCo: Program Helps Self-Correction of Large Language Models

The performance of large language models in domain-specific tasks necessitates fine-tuning, which is computationally expensive and technically challenging. This paper focuses on parameter-efficient fine-tuning using soft prompting, a promising approach that adapts pre-trained models to downstream tasks by learning a small set of parameters. We propose a novel Input Dependent Soft Prompting technique with a self-Attention Mechanism (ID-SPAM) that generates soft prompts based on the input tokens and attends different tokens with varying importance. Our method is simple and efficient, keeping the number of trainable parameters small. We show the merits of the proposed approach compared to state-of-the-art techniques on various tasks and show the improved zero shot domain transfer capability.

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs

Retrieval-Augmented Generation (RAG) has proven effective in enhancing the factuality of LLMs' generation, making them a focal point of research. However, previous RAG approaches overlook the lexical diversity of queries, hindering their ability to achieve a granular relevance assessment between queries and retrieved documents, resulting in suboptimal performance. In this paper, we introduce a Lexical Diversity-aware RAG (DRAG) method to address the biases in relevant information retrieval and utilization induced by lexical diversity. Specifically, a Diversity-sensitive Relevance Analyzer is proposed to decouple and assess the relevance of different query components (words, phrases) based on their levels of lexical diversity, ensuring precise and comprehensive document retrieval. Moreover, a Risk-guided Sparse Calibration strategy is further introduced to calibrate the generated tokens that is heavily affected by irrelevant content. Through these modules, DRAG is capable of effectively retrieving relevant documents and leverages their pertinent knowledge to refine the original results and generate meaningful outcomes. Extensive experiments on widely used benchmarks demonstrate the efficacy of our approach, yielding a 10.6% accuracy improvement on HotpotQA.

Lexical Diversity-aware Relevance Assessment for Retrieval-Augmented Generation

Neural machine translation (NMT) systems amplify lexical biases present in their training data, leading to artificially impoverished language in output translations. These language-level characteristics render automatic translations different from text originally written in a language and human translations, which hinders their usefulness in for example creating evaluation datasets. Attempts to increase naturalness in NMT can fall short in terms of content preservation, where increased lexical diversity comes at the cost of translation accuracy. Inspired by the reinforcement learning from human feedback framework, we introduce a novel method that rewards both naturalness and content preservation. We experiment with multiple perspectives to produce more natural translations, aiming at reducing machine and human translationese. We evaluate our method on English-to-Dutch literary translation, and find that our best model produces translations that are lexically richer and exhibit more properties of human-written language, without loss in translation accuracy.

Downloads

Next from ACL 2025

TigerLLM - A Family of Bangla Large Language Models

Similar lecture

How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench