Austria

LLMs have gained immense popularity among researchers and the general public for its impressive capabilities on a variety of tasks. Notably, the efficacy of LLMs remains significantly dependent on the quality and structure of the input prompts, making prompt design a critical factor for their performance. Recent advancements in automated prompt optimization have introduced diverse techniques that automatically enhance prompts to better align model outputs with user expectations. However, these methods often suffer from the lack of standardization and compatibility across different techniques, limited flexibility in customization, inconsistent performance across model scales, and they often exclusively rely on expensive proprietary LLM APIs. To fill in this gap, we introduce GREATERPROMPT, a novel framework that democratizes prompt optimization by unifying diverse methods under a unified, customizable API while delivering highly effective prompts for different tasks. Our framework flexibly accommodates various model scales by leveraging both text feedback-based optimization for larger LLMs and internal gradient-based optimization for smaller models to achieve powerful and precise prompt improvements. Moreover, we provide a user-friendly Web UI that ensures accessibility for non-expert users, enabling broader adoption and enhanced performance across various user groups and application scenarios. GREATERPROMPT is available at https://github.com/psunlpgroup/GreaterPrompt via GitHub, PyPI, and web user interfaces.

ACL 2025

GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization

prompt optimization

large language models

natural language processing

### 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)

demo

Innovative transformer-based language models produce contextually-aware token embeddings and have achieved state-of-the-art performance for a variety of natural language tasks, but have been shown to encode unwanted biases for downstream applications. In this paper, we evaluate the social biases encoded by transformers trained with the masked language modeling objective using proposed proxy functions within an iterative masking experiment to measure the quality of transformer models’ predictions and assess the preference of MLMs towards disadvantaged and advantaged groups. We find that all models encode concerning social biases. We compare bias estimations with those produced by other evaluation methods using benchmark datasets and assess their alignment with human annotated biases. We extend previous work by evaluating social biases introduced after retraining an MLM under the masked language modeling objective and find proposed measures produce more accurate and sensitive estimations of biases based on relative preference for biased sentences between models, while other methods tend to underestimate biases after retraining on sentences biased towards disadvantaged groups.

Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality

Large Language Models (LLMs) have demonstrated strong performance in handling complex tasks that require both extensive knowledge and reasoning abilities. However, the existing LLM inference pipeline operates as an opaque process without explicit separation between knowledge retrieval and reasoning steps, making the model’s decision-making process unclear and disorganized. Recent research has shown that this ambiguity will lead to issues such as knowledge forgetting, which significantly impact the reliability of LLMs. In this paper, we propose a novel language model inference paradigm that decomposes the complex inference process into two distinct and clear actions: \textbf{(1) memory recall}: which retrieves relevant knowledge in LLM, and \textbf{(2) reasoning}: which performs reasoning steps based on the recalled knowledge. To facilitate this decomposition, we introduce two special tokens \textbf{$\langle \text{memory} \rangle$} and \textbf{$\langle \text{reason} \rangle$}, guiding the model to distinguish between steps that require knowledge retrieval and those that involve reasoning. Our experiment results show that this decomposition not only improves LLMs' performance among utility benchmarks but also enhances interpretability during the inference process, enabling users to identify sources of error and refine model responses effectively. The code is available at: https://github.com/MingyuJ666/Disentangling-Memory-and-Reasoning.

Disentangling Memory and Reasoning Ability in Large Language Models

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious prompts. While current methods effectively address jailbreak risks, they share common limitations: 1) Judging harmful outputs from the prefill-level lacks utilization of the model's decoding outputs, leading to relatively lower effectiveness and robustness. 2) Rejecting potentially harmful outputs based on a single evaluation can significantly impair the model's helpfulness. To address the above issues, we examine LLMs' capability to recognize harmful outputs, revealing and quantifying their proficiency in assessing the danger of previous tokens. Motivated by pilot experiment results, we design a robust defense mechanism at the decoding level. Our novel decoder-oriented, step-by-step defense architecture corrects the outputs of harmful queries directly rather than rejecting them outright. We introduce speculative decoding to enhance usability and facilitate deployment to boost safe decoding speed. Extensive experiments demonstrate that our approach improves model security without compromising reasoning speed. Notably, our method leverages the model's ability to discern hazardous information, maintaining its helpfulness compared to existing methods.

Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and time-consuming. Also, they have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt. To this end, we propose a method called POUGH that incorporates an efficient optimization algorithm and two semantics-guided prompt organization strategies. Specifically, our method starts with a sampling strategy to select representative prompts from a candidate pool, followed by a ranking strategy that prioritizes them. Given the sequentially ranked prompts, our method employs an iterative optimization algorithm to generate a fixed suffix that can concatenate to arbitrary user prompts for universal goal hijacking. Experiments conducted on four popular LLMs and ten types of target responses verified the effectiveness.

Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization

Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting court decision-making and improving judicial efficiency. However, existing methods often struggle with logical errors when conducting complex legal reasoning. We propose LegalReasoner, which enhances LJP reliability through step-wise verification and correction of the reasoning process. Specifically, it first identifies dispute points to decompose complex cases, and then conducts step-wise reasoning while employing a process verifier to validate each step's logic from correctness, progressiveness, and potential perspectives. When errors are detected, expert-designed attribution and resolution strategies are applied for correction. To fine-tune LegalReasoner, we release the LegalHK dataset, containing 58,130 Hong Kong court cases with detailed annotations of dispute points, step-by-step reasoning chains, and process verification labels. Experiments demonstrate that LegalReasoner significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B. The data is available at https://huggingface.co/datasets/weijiezz/LegalHK.

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning

Although large language models demonstrate strong performance across various domains, they still struggle with numerous bad cases in mathematical reasoning. Previous approaches to learning from errors synthesize training data by solely extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases. This paper presents Self-Error-Instruct (SEI), a framework that addresses these model weaknesses and synthesizes more generalized targeted training data. Specifically, we explore a target model on two mathematical datasets, GSM8K and MATH, to pinpoint bad cases. Then, we generate error keyphrases for these cases based on the instructor model’s (GPT-4o) analysis and identify error types by clustering these keyphrases. Next, we sample a few bad cases during each generation for each identified error type and input them into the instructor model, which synthesizes additional training data using a self-instruct approach. This new data is refined through a one-shot learning process to ensure that only the most effective examples are kept. Finally, we use these curated data to fine-tune the target model, iteratively repeating the process to enhance performance. We apply our framework to various models and observe improvements in their reasoning abilities across both in-domain and out-of-domain mathematics datasets. These results demonstrate the effectiveness of self-error instruction in improving LLMs’ mathematical reasoning through error generalization.

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning

Recent advances in Pretrained Language Models (PLMs) and Large Language Models (LLMs) have demonstrated transformative capabilities across diverse domains. The field of patent analysis and innovation is not an exception, where natural language processing (NLP) techniques presents opportunities to streamline and enhance important tasks---such as patent classification and patent retrieval---in the patent cycle. This not only accelerates the efficiency of patent researchers and applicants, but also opens new avenues for technological innovation and discovery. Our survey provides a comprehensive summary of recent NLP-based methods---including multimodal ones---in patent analysis. We also introduce a novel taxonomy for categorization based on tasks in the patent life cycle, as well as the specifics of the methods. This interdisciplinary survey aims to serve as a comprehensive resource for researchers and practitioners who work at the intersection of NLP, Multimodal AI, and patent analysis, as well as patent offices to build efficient patent systems.

A Survey on Patent Analysis: From NLP to Multimodal AI

With the continuously expanding parameters, efficiently adapting large language models to downstream tasks is crucial in resource-limited conditions. Many parameter-efficient fine-tuning methods have emerged to address this challenge. However, they lack flexibility, like LoRA requires manually selecting trainable parameters and rank size, (IA)$^{3}$ can only scale the activations along columns, yielding inferior results due to less precise fine-tuning. To address these issues, we propose a novel method named AdaDHP with fewer parameters and finer granularity, which can adaptively select important parameters for each task. Specifically, we introduce two trainable vectors for each parameter and fine-tune the parameters through Hadamard product along both rows and columns. This significantly reduces the number of trainable parameters, with our parameter count capped at the lower limit of LoRA. Moreover, we design an adaptive parameter selection strategy to select important parameters for downstream tasks dynamically. This allows our method to flexibly remove unimportant parameters for downstream tasks. Finally, we demonstrate the superiority of our method on the T5-base model across 17 NLU tasks and on complex mathematical tasks with the Llama series models.

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPl-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.

ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

With the rapid development of Multimodal Large Language Models (MLLMs), their potential in Chinese Classical Studies (CCS), a field which plays a vital role in preserving and promoting China’s rich cultural heritage, remains largely unexplored due to the absence of specialized benchmarks. To bridge this gap, we propose MCS-Bench, the first-of-its-kind multimodal benchmark specifically designed for CCS across multiple subdomains. MCS-Bench spans seven core subdomains (Ancient Chinese Text, Calligraphy, Painting, Oracle Bone Script, Seal, Cultural Relic, and Illustration), with a total of 45 meticulously designed tasks. Through extensive evaluation of 37 representative MLLMs, we observe that even the top-performing model (InternVL2.5-78B) achieves an average score below 50, indicating substantial room for improvement. Our analysis reveals significant performance variations across different tasks and identifies critical challenges in areas such as Optical Character Recognition (OCR) and cultural context interpretation. MCS-Bench not only establishes a standardized baseline for CCS-focused MLLM research but also provides valuable insights for advancing cultural heritage preservation and innovation in the Artificial General Intelligence (AGI) era. Data and code will be publicly available.

Downloads

Next from ACL 2025

Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality

Similar lecture

iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop