Breaking Focus: Contextual Distraction Curse in Large Language Models

Recent advances in Large Language Models (LLMs) have revolutionized generative systems, achieving excellent performance across diverse domains. Although these models perform well in controlled environments, their real-world applications frequently encounter inputs containing both essential and irrelevant details. Our investigation has revealed a critical vulnerability in LLMs, which we term Contextual Distraction Vulnerability (CDV). This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context. To systematically investigate this vulnerability, we propose an efficient tree-based search methodology to automatically generate CDV examples. Our approach successfully generates CDV examples across four datasets, causing an average performance degradation of approximately 45% in state-of-the-art LLMs. To address this critical issue, we explore various mitigation strategies and find that post-targeted training approaches can effectively enhance model robustness against contextual distractions. Our findings highlight the fundamental nature of CDV as an ability-level challenge rather than a knowledge-level issue since models demonstrate the necessary knowledge by answering correctly in the absence of distractions. This calls the community's attention to address CDV during model development to ensure reliability. The code is available at https://github.com/wyf23187/LLM_CDV.

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as the number of ICL demonstrations increases from a few to many, performance tends to plateau and eventually decline. We identify two primary causes for this trend: the suboptimal negative log-likelihood (NLL) optimization objective and the incremental data noise. To address these issues, we introduce DR-ICL, a novel optimization method that enhances model performance through Differentiated Learning and advantage-based Reweighting objectives. Globally, DR-ICL utilizes differentiated learning to optimize the NLL objective, ensuring that many-shot performance surpasses zero-shot levels. Locally, it dynamically adjusts the weighting of many-shot demonstrations by leveraging cumulative advantages inspired by reinforcement learning, thereby improving generalization. This approach allows the model to handle varying numbers of shots effectively, mitigating the impact of noisy data. Recognizing the lack of multi-task datasets with diverse many-shot distributions, we develop the Many-Shot ICL Benchmark (MICLB)-a large-scale benchmark covering shot numbers from 1 to 350 within sequences of up to 8,000 tokens-for fine-tuning purposes. MICLB facilitates the evaluation of many-shot ICL strategies across seven prominent NLP tasks and 50 distinct datasets. Experimental results demonstrate that LLMs enhanced with DR-ICL achieve significant improvements in many-shot setups across various tasks, including both in-domain and out-of-domain scenarios. We release the code and benchmark dataset hoping to facilitate further research in many-shot ICL.

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to develop effective defense strategies. We aim to shed more light into this issue: we conduct a detailed large-scale analysis of seven different jailbreak methods and find that these disagreements stem from insufficient observation samples. In particular, we introduce \textit{safety boundary}, and we find that jailbreaks shift harmful activations outside that safety boundary, where LLMs are less sensitive to harmful information. We also find that the low and the middle layers are critical in such shifts, while deeper layers have less impact. Leveraging on these insights, we propose a novel defense called \textbf{Activation Boundary Defense} (ABD), which adaptively constrains the activations within the safety boundary. We further use Bayesian optimization to selectively apply the defense method to the low and the middle layers. Our experiments on several benchmarks show that ABD achieves an average DSR of over 98\% against various forms of jailbreak attacks, with less than 2\% impact on the model's general capabilities.

AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?

Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information, facilitating a wide range of complex applications and tasks. However, the evaluation of LVLMs presents significant challenges as the evaluation benchmark always demands lots of human cost for its construction, and remains static, lacking flexibility once constructed. Even though automatic evaluation has been explored in textual modality, the visual modality remains under-explored. As a result, in this work, we address a question: "Can LVLMs serve as a path to automatic benchmarking?". We introduce AutoBench-V, an automated framework for serving evaluation on demand, i.e., benchmarking LVLMs based on specific aspects of model capability. Upon receiving an evaluation capability, AutoBench-V leverages text-to-image models to generate relevant image samples and then utilizes LVLMs to orchestrate visual question-answering (VQA) tasks, completing the evaluation process efficiently and flexibly. Through an extensive evaluation of seven popular LVLMs across five demanded user inputs (i.e., evaluation capabilities), the framework shows effectiveness and reliability. We observe the following: (1) Our constructed benchmark accurately reflects varying task difficulties; (2) As task difficulty rises, the performance gap between models widens; (3) While models exhibit strong performance in abstract level understanding, they underperform in details reasoning tasks; and (4) Constructing a dataset with varying levels of difficulties is critical for a comprehensive and exhaustive evaluation. Overall, AutoBench-V not only successfully utilizes LVLMs for automated benchmarking but also reveals that LVLMs as judges have significant potential in various domains.

From a Tiny Slip to a Giant Leap: An LLM-Based Simulation for Fake News Evolution

With the growing spread of misinformation online, research has increasingly focused on detecting and tracking fake news. However, an overlooked issue is that fake news does not naturally exist in social networks -- it often originates from distorted facts or deliberate fabrication by malicious actors. Understanding how true news gradually evolves into fake news is critical for early detection and prevention, reducing its spread and impact. Hence, in this paper, we take the first step toward simulating and revealing this evolution, proposing a Fake News evolUtion Simulation framEwork (FUSE) based on large language models (LLMs). Specifically, we employ LLM as agents to represent individuals in a simulated social network. We define four types of agents commonly observed in daily interactions: spreaders, who propagate information; commentators, who provide opinions and interpretations; verifiers, who check the accuracy of information; and bystanders, who passively observe without engaging. For simulated environments, we model various social network structures, such as high-clustering networks and scale-free networks, to mirror real-world network dynamics. Each day, the agents engage in belief exchanges, reflect on their thought processes, and reintroduce the news accordingly. Given the lack of prior work in this area, we developed a FUSE-EVAL evaluation framework to measure the deviation from true news during the fake news evolution process. The results show that FUSE successfully captures the underlying patterns of how true news transforms into fake news and accurately reproduces previously discovered instances of fake news, aligning closely with human evaluations. Moreover, our work provides insights into the fact that combating fake news should not be delayed until it has fully evolved; instead, prevention in advance is key to achieving better outcomes.

QUIDS: Query Intent Generation via Dual Space Modeling

Query understanding is a crucial component of Information Retrieval (IR), aimed at identifying the underlying search intent of textual queries. However, most existing approaches oversimplify this task into query classification or clustering, which fails to fully capture the nuanced intent behind the query. In this paper, we address the task of query intent generation: to automatically generate detailed and precise intent descriptions for search queries using relevant and irrelevant documents given a query. These intent descriptions can help users understand why the search engine considered the top-ranked documents relevant, and provide more transparency to the retrieval process. We propose a dual-space model that uses semantic relevance and irrelevance information in the returned documents to explain the understanding of the query intent. Specifically, in the encoding process, we project, separate, and distinguish relevant and irrelevant documents in the representation space. Then, we introduce a semantic decoupling model in the novel disentangling space, where the semantics of irrelevant information are removed from the relevant space, ensuring that only the essential and relevant intent is captured. This process refines the understanding of the query and provides more accurate explanations for the search results. Experiments on benchmark data demonstrate that our methods produce high-quality query intent descriptions, outperforming existing methods for this task, as well as state-of-the-art query-based summarization methods. A token-level visualization of attention scores reveals that our model effectively reduces the focus on irrelevant intent topics. Our findings open up promising research and application directions for query intent generation, particularly in exploratory search.

Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks

The impact of social media on critical issues such as echo chambers needs to be addressed, as these phenomena can have disruptive consequences for our society. Traditional research often oversimplifies emotional tendencies and opinion evolution into numbers and formulas, neglecting that news and communication are conveyed through text, which limits these approaches. Hence, in this work, we propose an LLM-based simulation for the social opinion network to evaluate and counter polarization phenomena. We first construct three typical network structures to simulate different characteristics of social interactions. Then, agents interact based on recommendation algorithms and update their strategies through reasoning and analysis. By comparing these interactions with the classic Bounded Confidence Model (BCM), the Friedkin Johnsen (FJ) model, and using echo chamber-related indices, we demonstrate the effectiveness of our framework in simulating opinion dynamics and reproducing phenomena such as opinion polarization and echo chambers. We propose two mitigation methods, active and passive nudges, that can help reduce echo chambers, specifically within language-based simulations. We hope our work will offer valuable insights and guidance for social polarization mitigation.

ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering

Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. Correspondingly, we introduce a QAMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data. We first address the issue of imbalanced label distribution by re-weighting the instance-wise loss based on the inverse frequency of each class, ensuring minority classes are not dominated by majority ones during optimization. Next, we utilize the unlabeled data to enrich the learning process, generating a variety of augmentations based on a SoftMix operation and ensuring their predictions align with the same target, i.e., pseudo-labels. To ensure the quality of the pseudo-labels, we propose a calibration procedure aimed at closely aligning the pseudo-label estimates of individual samples with a desired ground truth distribution. Experiments show that our QAMatch significantly outperforms the recent similar-scale baselines and Large Language Models (LLMs) not only on our ScholarChemQA dataset but also on four benchmark datasets. We hope our benchmark and model can facilitate and promote more research on chemical QA.

Advanced Framework for Animal Sound Classification With Features Optimization

The automatic classification of animal sounds presents an enduring challenge in bioacoustics, owing to the diverse statistical properties of sound signals, variations in recording equipment, and prevalent low Signal-to-Noise Ratio (SNR) conditions. Deep learning models like Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) have excelled in human speech recognition but have not been effectively tailored to the intricate nature of animal sounds, which exhibit substantial diversity even within the same domain. We propose an automated classification framework applicable to general animal sound classification. Our approach first optimizes audio features from Mel-frequency cepstral coefficients (MFCC) including feature rearrangement and feature reduction. It then uses the optimized features for the deep learning model, i.e., an attention-based Bidirectional LSTM (Bi-LSTM), to extract deep semantic features for sound classification. We also contribute an animal sound benchmark dataset encompassing oceanic animals and birds1. Extensive experimentation with real-world datasets demonstrates that our approach consistently outperforms baseline methods by over 25% in precision, recall, and accuracy, promising advancements in animal sound classification.

What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks

Tool learning methods have enhanced the ability of large language models (LLMs) to interact with real-world applications. Many existing works fine-tune LLMs or design prompts to enable LLMs to select appropriate tools and correctly invoke them to meet user requirements. However, it is observed in previous works that the performance of tool learning varies from tasks, datasets, training settings, and algorithms. Without understanding the impact of these factors, it can lead to inconsistent results, inefficient model deployment, and suboptimal tool utilization, ultimately hindering the practical integration and scalability of LLMs in real-world scenarios. Therefore, in this paper, we explore the impact of both internal and external factors on the performance of tool learning frameworks. Through extensive experiments on two benchmark datasets, we find several insightful conclusions for future work, including the observation that LLMs can benefit significantly from increased trial and exploration. We believe our empirical study provides a new perspective for future tool learning research.