United States

Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsible AI behaviors. However, the process typically requires substantial data and computation resources. Recent studies have revealed that alignment might be attainable at lower costs through simpler methods, such as in-context learning. This leads to the question: Is alignment predominantly superficial? In this paper, we delve into this question and provide a quantitative analysis. We formalize the concept of superficial knowledge, defining it as knowledge that can be acquired through easily token restyling, without affecting the model’s ability to capture underlying causal relationships between tokens. We propose a method to extract and isolate those superficial knowledge from aligned models, focusing on the shallow modifications to the final token selection process. By comparing models augmented only with superficial knowledge to fully aligned models, we quantify the superficial portion of alignment. Our findings reveal that while superficial knowledge constitutes a significant portion of alignment, particularly in safety and detoxification tasks, it is not the whole story. Tasks requiring reasoning and contextual understanding still rely on deeper knowledge. Additionally, we demonstrate two practical advantages of isolated superficial knowledge: (1) it can be transferred between models, enabling efficient offsite alignment of larger models using extracted superficial knowledge from smaller models, and (2) it is recoverable, allowing for the restoration of alignment in compromised models without sacrificing performance.

NAACL 2025

Extracting and Understanding the Superficial Knowledge in Alignment

alignment

safety

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

poster

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability—users have minimal influence over the downstream task, as they can only modify input images, while the training of VLMs is often out of reach for most researchers. (ii) Lack of explainability—it is difficult to trace VLM errors to specific causes, such as failures in visual encoding or reasoning. We propose TextFlow, addressing aforementioned issues with two stages: (i) Vision Textualizer—which generates textual representations from flowchart images; and (ii) Textual Reasoner—which performs question-answering based on the text representations. TextFlow offers three key advantages: (i) users can select the type of text representations (e.g., Graphviz, Mermaid, PlantUML), or further convert them into executable graph object to call tools, enhancing performance and controllability; (ii) it improves explainability by helping to attribute errors more clearly to visual or textual processing components; and (iii) it promotes the modularization of the solution, such as allowing advanced LLMs to be used in the reasoner stage when VLMs underperform in end-to-end fashion. Experiments on the FlowVQA and FlowLearn benchmarks demonstrate TextFlow's state-of-the-art performance as well as its robustness. All code and data are publicly available.

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

Large language models are known to hallucinate, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In this work, we find that unfamiliar examples in the models' finetuning data -- those that introduce concepts beyond the base model's scope of knowledge -- are crucial in shaping these errors. In particular, we find that an LLM's hallucinated predictions tend to mirror the responses associated with its unfamiliar finetuning examples. This suggests that by modifying how unfamiliar finetuning examples are supervised, we can influence a model's responses to unfamiliar queries (e.g., say ''I don't know''). We empirically validate this observation in a series of controlled experiments involving SFT, RL, and reward model finetuning on TriviaQA and MMLU. Our work further investigates RL finetuning strategies for improving the factuality of long-form model generations. We find that, while hallucinations from the reward model can significantly undermine the effectiveness of RL factuality finetuning, strategically controlling how reward models hallucinate can minimize these negative effects. Leveraging our previous observations on controlling hallucinations, we propose an approach for learning more reliable reward models, and show that they improve the efficacy of RL factuality finetuning in long-form biography and book/movie plot generation tasks.

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

We introduce CluSanT, a novel text sanitization framework based on Metric Local Differential Privacy (MLDP). Our framework consists of three components: token clustering, cluster embedding, and token sanitization. For the first, CluSanT employs Large Language Models (LLMs) to create---a set of potential substitute tokens which we meaningfully cluster. Then, we develop a parameterized cluster embedding that balances the trade-off between privacy and utility. Lastly, we propose a MLDP algorithm which sanitizes/substitutes sensitive tokens in a text with the help of our embedding. Notably, our MLDP-based framework can be tuned with parameters such that (1) existing state-of-the-art (SOTA) token sanitization algorithms can be described---and improved---via our framework with extremal values of our parameters, and (2) by varying our parameters, we allow for a whole spectrum of privacy-utility tradeoffs between the two SOTA. Our experiments demonstrate CluSanT's balance between privacy and semantic coherence, highlighting its capability as a valuable framework for privacy-preserving text sanitization.

CluSanT: Differentially Private and Semantically Coherent Text Sanitization

There are more than 300 documented signed languages worldwide, which are indispensable avenues for computational linguists to study cross-cultural and cross-linguistic factors that affect automatic sign understanding and generation. Yet, these are studied under critically low-resource settings, especially when examining multiple signed languages simultaneously. In this work, we hypothesize that a linguistically informed alignment algorithm can improve the results of sign-to-sign translation models. To this end, we first conduct a qualitative analysis of similarities and differences across three signed languages: American Sign Language (ASL), Chinese Sign Language (CSL), and German Sign Language (DGS). We then introduce a novel generation and alignment algorithm for translating one sign language to another, exploring Large Language Models (LLMs) as intermediary translators and paraphrasers. We also compile a dataset of sign-to-sign translation pairs between these signed languages. Our model trained on this dataset performs well on automatic metrics for sign-to-sign translation and generation. Our code and data will be available for the camera-ready version of the paper.

How to Align Multiple Signed Language Corpora for Better Sign-to-Sign Translations?

Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: {i} They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. {ii} Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correlates positively with memory usage and computational costs. Achieving high efficiency and performance remains an ongoing challenge. To address these issues, we propose a novel Low-parameters Prompt Tuning (LAMP) method, which leverages prompt decomposition and compressed outer product. Specifically, the prompt decomposition module employs Truncated SVD to reduce training parameters and significantly lower the dimensionality of the soft prompt parameter space. It then utilizes a compressed outer product module to facilitate multiple interactions among prompt tokens, exploring their intrinsic associations to enhance knowledge representation. Finally, LAMP uses average pooling to reduce memory usage and training/inference time. Extensive experiments across six architectures and eight datasets demonstrate that LAMP outperforms state-of-the-art PT-based and LoRA-based methods in performance and efficiency.

Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product

As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorithms are escalating significantly. In this paper, we propose modeling the changes at the logits level during post-training using a separate neural network (i.e., the value network). After training this network on a small base model using demonstrations, this network can be seamlessly integrated with another pre-trained models during inference, enabling them to achieve similar capability enhancements. We systematically investigate the best practices for this paradigm in terms of pre-training weights and connection schemes. We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes within the same family, models undergoing continuous pre-training within the same family, and models with different vocabularies across families. In certain cases, it can achieve performance comparable to full-parameter fine-tuning. Furthermore, we explore training methods to enhance transferability, which effectively improve the transfer performance of the value model across models of various parameter scales and prevent overfitting to the base model used during training.

Transferable Post-training via Inverse Value Learning

The widespread application of Large Language Models (LLMs) across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, such as Reinforcement Learning with Human Feedback (RLHF), constitutional learning, and safety fine-tuning etc., there is an urgent need to understand the scope and nature of human values injected into these LLMs before their deployment and adoption. We propose UniVar, a high-dimensional neural representation of symbolic human value distributions in LLMs, orthogonal to model architecture and training data. This is a continuous and scalable representation, self-supervised from the value-relevant output of 8 LLMs and evaluated on 15 open-source and commercial LLMs. Through UniVar, we visualize and explore how LLMs prioritize different values in 25 languages and cultures, shedding light on the complex interplay between human values and language modeling.

High-Dimension Human Value Representation in Large Language Models

The use of AI in legal analysis and prediction (LegalAI) has gained attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and underutilize the capabilities of modern large language models (LLMs). In this paper, inspired by the debate phase of real courtroom trials, we propose a novel legal judgment prediction model based on the Debate-Feedback architecture, which integrates LLM multi-agent debate and reliability evaluation models. Unlike traditional methods, our model achieves significant improvements in efficiency by minimizing the need for large historical datasets, thus offering a lightweight yet robust solution. Comparative experiments show that it outperforms several general-purpose and domain-specific legal models, offering a dynamic reasoning process and a promising direction for future LegalAI research.

Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction

Legal judgment prediction (LJP) is an essential task for legal AI, aiming at predicting judgments based on the facts of a case. Legal judgments can involve multiple law articles and charges. Although recent methods in LJP have made notable progress, most are constrained to single-task settings (e.g., only predicting charges) or single-label settings (e.g., not accommodating cases with multiple charges), diverging from the complexities of real-world scenarios. In this paper, we address the challenge of predicting relevant law articles and charges within the framework of legal judgment prediction, treating it as a multi-task and multi-label text classification problem. We introduce a knowledge-enhanced approach, called K-LJP, that incorporates (I) ''label-level knowledge'' (such as definitions and relationships among labels) to enhance the representation of case facts for each task, and (ii) ''task-level knowledge'' (such as the alignment between law articles and corresponding charges) to improve task synergy. Comprehensive experiments demonstrate our method's effectiveness in comparison to state-of-the-art (SOTA) baselines.

Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. Pruning can reduce model size, yet existing methods assume public access to calibration data, which is impractical for privacy-sensitive applications. To address the challenge of pruning LLMs in privacy-preserving settings, we propose FedSpaLLM, the first federated learning framework designed specifically for pruning LLMs. FedSpaLLM enables clients to locally prune their models based on private data while accounting for system heterogeneity and maintaining communication efficiency. Our framework introduces several key innovations: (1) a novel \ell_0-norm aggregation function that ensures only non-zero weights are averaged across clients, preserving important model parameters; (2) an adaptive mask expansion technique that meets global sparsity targets while accommodating client-specific pruning decisions; and (3) a layer sampling strategy that reduces communication overhead and personalizes the pruning process based on client resources. Extensive experiments show that FedSpaLLM improves pruning performance in diverse federated settings.

Downloads

Next from NAACL 2025

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

Similar lecture

Are Prompt-based Models Clueless?