Austria

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during pre-training. We systematically explored the existence and measurement of forgetting in pre-training, questioning traditional metrics such as perplexity (PPL) and introducing new metrics to better detect entity memory retention. Based on our revised assessment of forgetting metrics, we explored low-cost, straightforward methods to mitigate forgetting during the pre-training phase. In addition, we carefully analyzed the learning curves, offering insights into the dynamics of forgetting. Extensive evaluations and analyses on forgetting of pre-training could facilitate future research on LLMs.

ACL 2025

Exploring Forgetting in Large Language Model Pre-Training

counter-intuitive

systematic exploration

forgetting

pretraining

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

technical paper

### 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)

Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable to simple perturbations and adversarial attacks. To build an effective defense against malicious perturbations, we view MGT detection from a threat modeling perspective, that is, analyzing the model’s vulnerability from an adversary’s point of view and exploring effective mitigations. To this end, we introduce an adversarial framework for training a robust MGT detector, named GREedy Adversary PromoTed DefendER (GREATER). The GREATER consists of two key components: an adversary GREATER-A and a detector GREATER-D. The GREATER-D learns to defend against the adversarial attack from GREATER-A and generalizes the defense to other attacks. GREATER-A identifies and perturbs the critical tokens in embedding space, along with greedy search and pruning to generate stealthy and disruptive adversarial examples. Besides, we update the GREATER-A and GREATER-D synchronously, encouraging the GREATER-D to generalize its defense to different attacks and varying attack intensities. Our experimental results across 10 text perturbation strategies and 6 adversarial attacks show that our GREATER-D reduces the Attack Success Rate (ASR) by 0.67% compared with SOTA defense methods while our GREATER-A is demonstrated to be more effective and efficient than SOTA attack approaches. Codes and dataset are available in https://github.com/Liyuuuu111/GREATER.

Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training

Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variations, they still struggle with efficient and effective parameter-wise learning rate estimation, resulting in training instability, slow convergence, and poor compatibility with parameter-efficient fine-tuning (PEFT) techniques. This work introduces Scaling with Gradient Grouping (SGG), an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling. SGG first groups gradient statistics in each layer into clusters and then applies cluster-specific scaling to calibrate learning rates for each parameter, thus imposing collective group-wise constraints while maintaining precise per-parameter adaptation. Experiments on diverse (M)LLM benchmarks show that SGG integrates seamlessly with existing optimizers, and offers consistent gains and faster convergence over baselines, with various model sizes. Its stability across varying batch sizes and learning rates establishes SGG as a robust choice for LLM optimization.

Taming LLMs with Gradient Grouping

Language models hold incredible promise for enabling scientific discovery by synthesizing massive research corpora. Many complex scientific research questions have multiple plausible answers, each supported by evidence of varying strength. However, existing language models lack the capability to quantitatively and faithfully compare answer plausibility in terms of supporting evidence. To address this, we introduce Retrieve to Explain (R2E), a retrieval-based model that scores and ranks all possible answers to a research question based on evidence retrieved from a document corpus. The architecture represents each answer only in terms of its supporting evidence, with the answer itself masked. This allows us to extend feature attribution methods such as Shapley values, to transparently attribute answer scores to supporting evidence at inference time. The architecture also allows incorporation of new evidence without retraining, including non-textual data modalities templated into natural language. We developed R2E for the challenging scientific discovery task of drug target identification, a human-in-the-loop process where failures are extremely costly and explainability paramount. When predicting whether drug targets will subsequently be confirmed as efficacious in clinical trials, R2E not only matches non-explainable literature-based models but also surpasses a genetics-based target identification approach used throughout the pharmaceutical industry.

Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target Identification

Traditional methods for processing classical Chinese typically segment language understanding into discrete tasks, which overlook crucial background information and reduce user engagement. Large language models (LLMs) provide integrated solutions, yet they entail high computational costs and risks of generating inaccurate historical information. To tackle these challenges, we propose a novel framework, TEACH (conTrastive knowlEdge Adaptive distillation with enhanCed Historical interpretability), which focuses on classical Chinese understanding by integrating word sense disambiguation with sentence translation. This integration leverages a confidence-annotated knowledge base and a step-by-step Chain-of-Thought prompting mechanism to minimize hallucinations and improve semantic analysis. Moreover, TEACH employs contrastive distillation learning to efficiently transfer capabilities from larger models to smaller ones (e.g., Qwen2-1.5B), addressing overly liberal translations. Additionally, we introduce an innovative generation evaluation metric using iterative word alignment, enhancing LLM performance assessments by distinguishing additional information and addressing excessive translation issues. Experiments conducted on real-world datasets validate TEACH's efficacy in classical Chinese educational scenarios.

TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Ancient Chinese Understanding

Large Language Models (LLMs) can correct their self-generated responses, but a decline in accuracy after self-correction is also witnessed. To have a deeper understanding of self-correction, we endeavor to decompose, evaluate, and analyze the self-correction behaviors of LLMs. By enumerating and analyzing answer correctness before and after self-correction, we decompose the self-correction capability into confidence (being confident to correct answers) and critique (turning wrong answers to correct) capabilities, and propose two metrics from a probabilistic perspective to measure these 2 capabilities, along with another metric for overall self-correction capability evaluation. Based on our decomposition and evaluation metrics, we conduct extensive experiments and draw some empirical conclusions. For example, we find different models can exhibit distinct behaviors: some models are confident while others are more critical. We also find the trade-off between the two capabilities (i.e. improving one can lead to a decline in the other) when manipulating model self-correction behavior by prompts or in-context learning. Further, we find a simple yet efficient strategy to improve self-correction capability by transforming Supervision Fine-Tuning (SFT) data format, and our strategy outperforms vanilla SFT in both capabilities and achieves much higher accuracy after self-correction.

Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs

In this work, we propose ProtoLens, a novel prototype-based model that provides fine-grained, sub-sentence level interpretability for text classification. ProtoLens uses a Prototype-aware Span Extraction module to identify relevant text spans associated with learned prototypes and a Prototype Alignment mechanism to ensure prototypes are semantically meaningful throughout training. By aligning the prototype embeddings with human-understandable examples, ProtoLens provides interpretable predictions while maintaining competitive accuracy. Extensive experiments demonstrate that ProtoLens outperforms both prototype-based and non-interpretable baselines on multiple text classification benchmarks. Code and data are available at \url{https://github.com/weibowen555/ProtoLens}.

ProtoLens: Advancing Prototype Learning for Fine-Grained Interpretability in Text Classification

Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations. Graph neural networks mainly depend on structural information, often overlooking semantic understanding and requiring high computational costs. Meanwhile, Large Language Models (LLMs) support zero-shot reasoning but lack sufficient capabilities to grasp the laws of historical event development. To tackle these challenges, we introduce a training-free Analogical Replay (AnRe) reasoning framework. Our approach retrieves similar events for queries through semantic-driven clustering and builds comprehensive historical contexts using a dual history extraction module that integrates long-term and short-term history. It then uses LLMs to generate analogical reasoning examples as contextual inputs, enabling the model to deeply understand historical patterns of similar events and improve its ability to predict unknown ones. Our experiments on four benchmarks show that AnRe significantly exceeds traditional training and existing LLM-based methods. Further ablation studies also confirm the effectiveness of the dual history extraction and analogical replay mechanisms.

AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the inherent trade-off between computational efficiency and chunking precision in LLM-based approaches, we devise the granularity-aware Mixture-of-Chunkers (MoC) framework, which consists of a three-stage processing mechanism. Notably, our objective is to guide the chunker towards generating a structured list of chunking regular expressions, which are subsequently employed to extract chunks from the original text. Extensive experiments demonstrate that both our proposed metrics and the MoC framework effectively settle challenges of the chunking task, revealing the chunking kernel while enhancing the performance of the RAG system.

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

Recent advancements in long chain-of-thoughts (long CoTs) have significantly improved the reasoning capabilities of large language models (LLMs). Existing work finds that the capability of long CoT reasoning can be efficiently elicited by tuning on only a few examples and can easily transfer to other tasks. This motivates us to investigate whether long CoT reasoning is a general capability for LLMs. In this work, we conduct an empirical analysis for this question from the perspective of representation. We find that LLMs do encode long CoT reasoning as a general capability, with a clear distinction from vanilla CoTs. Furthermore, domain-specific representations are also required for the effective transfer of long CoT reasoning. Inspired by these findings, we propose GLORE, a novel representation engineering method to unleash the general long CoT reasoning capabilities of LLMs. Extensive experiments demonstrate the effectiveness and efficiency of GLORE in both in-domain and cross-domain scenarios. The code is available at https://github.com/txy77/GLoRE.

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low reliability due to the extensive sequential UI interactions. To address this issue, we propose AXIS, a novel LLM-based agents framework that prioritize actions through application programming interfaces (APIs) over UI actions. This framework also facilitates the creation and expansion of APIs through automated exploration of applications. Our experiments on Microsoft Word demonstrate that AXIS reduces task completion time by 65%-70% and cognitive workload by 38%-53%, while maintaining accuracy of 97%-98% compared to humans. Our work contributes to a new human-agent-computer interaction (HACI) framework and explores a fresh UI design principle for application providers to turn applications into agents in the era of LLMs, paving the way towards an agent-centric operating system (Agent OS). The code and dataset will be available at https://aka.ms/haci_axis.

Downloads

Next from ACL 2025

Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training

Similar lecture

Domain adapted machine translation: What does catastrophic forgetting forget and why?