Association for the Advancement of Artificial Intelligence: AAAI Publications
Not a member yet
26155 research outputs found
Sort by
BeyondGender: A Multifaceted Bilingual Dataset for Practical Sexism Detection
No full textSexism affects both women and men, yet research often overlooks misandry and suffers from overly broad annotations that limit AI applications. To address this, we introduce BeyondGender, a dataset meticulously annotated according to the latest definitions of misogyny and misandry. It features innovative multifaceted labels encompassing aspects of sexism, gender, phrasing, misogyny, and misandry. The dataset includes 6K English and 1.7K Chinese sexism instances, alongside 13K non-sexism examples.
Our evaluations of masked language models and large language models reveal that they detect misogyny in English and misandry in Chinese more effectively, with F1-scores of 0.87 and 0.62, respectively. However, they frequently misclassify hostile and mild comments, underscoring the complexity of sexism detection. Parallel corpus experiments suggest promising data augmentation strategies to enhance AI systems for nuanced sexism detection, and our dataset can be leveraged to improve value alignment in large language models
Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
No full textLarge Language Model-based Dense Retrieval (LLM-DR) optimizes over numerous heterogeneous fine-tuning collections from different domains. However, the discussion about its training data distribution is still minimal. Previous studies rely on empirically assigned dataset choices or sampling ratios, which inevitably lead to sub-optimal retrieval performances. In this paper, we propose a new task-level Distributionally Robust Optimization (tDRO) algorithm for LLM-DR fine-tuning, targeted at improving the universal domain generalization ability by end-to-end reweighting the data distribution of each task. The tDRO parameterizes the domain weights and updates them with scaled domain gradients. The optimized weights are then transferred to the LLM-DR fine-tuning to train more robust retrievers. Experiments show optimal improvements in large-scale retrieval benchmarks and reduce up to 30% dataset usage after applying our optimization algorithm with a series of different-sized LLM-DR models
3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding
No full textAn essential component in Large Language Models (LLMs) is Rotary Position Encoding (RoPE) , which efficiently manages positional dependencies in long-context modeling. However, when the number of input tokens surpasses the pretrained capacity of LLMs, their ability to process and generate text is markedly weakened. Although position interpolation techniques for RoPE can mitigate this issue, an increase in interpolations leads to a decrease in positional resolution. To tackle this challenge, drawing inspiration from the Bloch Sphere representation, we propose a novel rotary position encoding on a three-dimensional sphere, named 3D Rotary Position Encoding (3D-RPE). 3D-RPE is an advanced version of the widely used 2D RoPE, with two major advantages for modeling long contexts: controllable long-term decay and improved position resolution. For controllable long-term decay, 3D-RPE allows for the regulation of long-term decay within the chunk size, ensuring the modeling of relative positional information between tokens at a distant relative position. For improved position resolution, 3D-RPE can mitigate the degradation of position resolution caused by position interpolation on RoPE. We have conducted experiments on long-context Natural Language Understanding (NLU) and long sequence Language Modeling (LM) tasks. From the experimental results, 3D-RPE achieved performance improvements over RoPE, especially in long-context NLU tasks
Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning
No full textAugmenting large language models (LLMs) with tools significantly enhances their problem-solving potential across multifaceted tasks.
However, current tools automatically created by LLMs often serve as a mere summary of specific problems or solutions, which face two main issues:
1) Low reusability: The tools are overly problem-specific and struggle to handle new problems.
2) Limited diversity: The toolsets are too narrow, limiting their application to address a broader range of different problems.
In this paper, we propose the Knowledge-grounded Tool Creation with Evolution (KTCE) framework, which aims to craft reusable and comprehensive toolsets for LLMs in a two-stage process.
In the first stage (Knowledge-based Tool Creation), we conceptualize tools as a form of executable domain knowledge and propose a problem-knowledge-tool paradigm.
Specifically, we leverage LLMs to abstract "knowledge" from "problems" and create a three-layer knowledge tree of topics, concepts, and key points. This hierarchical structure serves as a foundation for inducing atomic "tools" from "knowledge", grounding them in fundamental concepts and enhancing their usability.
In the second stage (Tool Evolutionary Search), we evolve the toolsets through several actions including tool selection, mutation, and crossover. This stage mimics the biological evolution process, aiding toolsets in discovering new tools or updating existing ones, thereby increasing the diversity of the toolset.
Experiments on challenging mathematical/tabular/scientific reasoning tasks demonstrate that our approach achieves substantial accuracy improvements ranging from 6.23% to 18.49% on average. Moreover, in-depth analyses reveal the superior characteristics of our toolkit, including high reusability, high diversity, and high generalizability on cross-data/LLM performance with low complexity
Training on the Benchmark Is Not All You Need
No full textThe success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests to become unreliable. If any model has been trained on a benchmark test set, it can seriously hinder the health of the field. In order to automate and efficiently test the capabilities of large language models, numerous mainstream benchmarks adopt a multiple-choice format. As the swapping of the contents of multiple-choice options does not affect the meaning of the question itself, we propose a simple and effective data leakage detection method based on this property. Specifically, we shuffle the contents of the options in the data to generate the corresponding derived data sets, and then detect data leakage based on the model's log probability distribution over the derived data sets. If there is a maximum and outlier in the set of log probabilities, it indicates that the data is leaked. Our method is able to work under gray-box conditions without access to model training data or weights, effectively identifying data leakage from benchmark test sets in model pre-training data, including both normal scenarios and complex scenarios where options may have been shuffled intentionally or unintentionally. Through experiments based on two LLMs and benchmark designs, we demonstrate the effectiveness of our method. In addition, we evaluate the degree of data leakage of 35 mainstream open-source LLMs on four benchmark datasets and give a ranking of the leaked LLMs for each benchmark, and we find that the Qwen family of LLMs has the highest degree of data leakage
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
No full textLarge Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as LLMs may inadvertently produce copyrighted material. In this paper, we first investigate the effectiveness of watermarking LLMs as a deterrent against the generation of copyrighted texts. Through theoretical analysis and empirical evaluation, we demonstrate that incorporating watermarks into LLMs significantly reduces the likelihood of generating copyrighted content, thereby addressing a critical concern in the deployment of LLMs. However, we also find that watermarking can have unintended consequences on Membership Inference Attacks (MIAs), which aim to discern whether a sample was part of the pretraining dataset and may be used to detect copyright violations. Surprisingly, we find that watermarking adversely affects the success rate of MIAs, complicating the task of detecting copyrighted text in the pretraining dataset. These results reveal the complex interplay between different regulatory measures, which may impact each other in unforeseen ways. Finally, we propose an adaptive technique to improve the success rate of a recent MIA under watermarking. Our findings underscore the importance of developing adaptive methods to study critical problems in LLMs with potential legal implications
Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization
No full textLarge Language Models (LLMs) have permeated various Natural Language Processing (NLP) tasks. For the summarization tasks, LLMs can generate well-structured rationales, which consist of Essential Aspects (EA), Associated Sentences (AS) and Triple Entity Relations (TER). These rationales guide smaller models (≤1B) to produce better summaries. However, their high deployment costs (≥70B), such as substantial storage space and high computing requirements, limit their utilization in resource-constrained environments. Furthermore, effectively distilling these structured rationales from LLMs into Small Language Models (SLMs) models remains a challenge. To address this, we propose the LLM-based Structured Rationale-guided Multi-view Weak-gated Fusion framework (LSR-MWF). The framework initially employs LLMs to dig structural rationales from a document, considering multiple viewpoints such as EA, AS, and TER. Then, it develop a multi-step summary generation evaluation strategy to select high-quality structured rationales. Subsequently, it aligns with these rationales using additional modules organized in a hierarchical structure. Finally, the framework integrates the features output by these modules with original abstractive model through a weak-gated mechanism. Experimental results on two publicly available CNN/DailyMail and XSum datasets show that our method improves the performance of the abstractive model, outperforming baselines by 11.2％ and 5.8％, respectively. In addition, our method improves the interpretability of summary generation from the viewpoints of EA, AS and TER
Int*-Match: Balancing Intra-Class Compactness and Inter-Class Discrepancy for Semi-Supervised Speaker Recognition
No full textOpen-set speaker recognition is to identify whether the voices are from the same speaker. One challenge of speaker recognition is collecting large amounts of high-quality data. Based on the promising results of image classification, one intuitively feasible solution is semi-supervised learning (SSL) which uses confidence thresholds to assign pseudo labels for unlabeled data. However, we empirically demonstrated that applying SSL methods to speaker recognition is non-trivial. These methods focus solely on inter-class discrepancy as thresholds to select pseudo labels, overlooking intra-class compactness, which is particularly important for open-set speaker recognition tasks. Motivated by this, we propose Int*-Match, a semi-supervised speaker recognition method selecting reliable pseudo labels with intra-class compactness and inter-class discrepancy for speaker recognition. In particular, we use the inter-class discrepancy of labeled data as the threshold for pseudo-label selection and adjust the threshold based on the intra-class compactness of the pseudo labels dynamically and adaptively. Our systematic experiments demonstrate the superiority of Int*-Match, presenting an outstanding Equal Error Rate (EER) of 1.00% on the VoxCeleb1 original test set, which is merely 0.06% below the performance achieved by fully supervised learning
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding
No full textMulti-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used applications. Compared with the traditional multi-modal conversations, MMC requires stronger character-centered understanding abilities as there are many interlocutors appearing in both the visual and textual context. To facilitate the study of this problem, we present Friends-MMC in this paper, an MMC dataset that contains 24,000+ unique utterances paired with video context. To explore the character-centered understanding of the dialogue, we also annotate the speaker of each utterance, the names and bounding bboxes of faces that appear in the video. Based on this Friends-MMC dataset, we further study two fundamental MMC tasks: conversation speaker identification and conversation response prediction, both of which have the multi-party nature with the video or image as visual context. For conversation speaker identification, we demonstrate the inefficiencies of existing methods such as pre-trained models, and propose a simple yet effective baseline method that leverages an optimization solver to utilize the context of two modalities to achieve better performance. For conversation response prediction, we fine-tune generative dialogue models on Friend-MMC, and analyze the benefits of speaker information. The code and dataset will be publicly available, and thus we call for more attention on modelling speaker information when understanding conversations
Enhancing Audiovisual Speech Recognition Through Bifocal Preference Optimization
No full textAudiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-world scenarios across various domains due to noisy acoustic environments, spontaneous speech, and the uncertain use of visual information. Most previous works fine-tune audio-only ASR models on audiovisual datasets, optimizing them for conventional ASR objectives. However, they often neglect visual features and common errors in unconstrained video scenarios. In this paper, we propose using a preference optimization strategy to improve speech recognition accuracy for real-world videos. First, we create preference data via simulating common errors that occurred in AV-ASR from two focals: manipulating the audio or vision input and rewriting the output transcript. Second, we propose BPO-AVASR, a Bifocal Preference Optimization method to improve AV-ASR models by leveraging both input-side and output-side preference. Extensive experiments demonstrate that our approach significantly improves speech recognition accuracy across various domains, outperforming previous state-of-the-art models on real-world video speech recognition