With advancements in large audio-language models (LALMs), which enhance large language models (LLMs) with auditory capabilities, these models are expected to demonstrate universal proficiency across various auditory tasks. While numerous benchmarks have emerged to assess LALMs’ performance, they remain fragmented and lack a structured taxonomy. To bridge this gap, we conduct a comprehensive survey and propose a systematic taxonomy for LALM evaluations, categorizing them into four dimensions based on their objectives: (1) General Auditory Awareness and Processing, (2) Knowledge and Reasoning, (3) Dialogue-oriented Ability, and (4) Fairness, Safety, and Trustworthiness. We provide detailed overviews within each category and highlight challenges in this field, offering insights into promising future directions. To the best of our knowledge, this is the first survey specifically focused on the evaluations of LALMs, providing clear guidelines for the community.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
This work addresses a fundamental barrier in recommender systems: the inability to generalize across domains without extensive retraining. Traditional ID-based approaches fail entirely in cold-start and cross-domain scenarios where new users or items lack sufficient interaction history. Inspired by foundation models’ cross-domain success, we develop a foundation model for sequential recommendation that achieves genuine zero-shot generalization capabilities. Our approach fundamentally departs from existing ID-based methods by deriving item representations exclusively from textual features. This enables immediate embedding of any new item without model retraining. We introduce unified item tokenization with Finite Scalar Quantization that transforms heterogeneous textual descriptions into standardized discrete tokens. This eliminates domain barriers that plague existing systems. Additionally, the framework features hybrid bidirectional-causal attention that captures both intra-item token coherence and inter-item sequential dependencies. An efficient catalog-aware beam search decoder enables real-time token-to-item mapping. Unlike conventional approaches confined to their training domains, RecGPT naturally bridges diverse recommendation contexts through its domain-invariant tokenization mechanism. Comprehensive evaluations across six datasets and industrial scenarios demonstrate consistent performance advantages.
Recent LLMs have demonstrated promising ability in solving finance related problems. However, applying LLMs in real-world finance application remains challenging due to its high risk and high stakes property. This paper introduces FinTrust, a comprehensive benchmark specifically designed for evaluating the trustworthiness of LLMs in finance applications. Our benchmark focuses on a wide range of alignment issues based on practical context and features fine-grained tasks for each dimension of trustworthiness evaluation. We assess eleven LLMs on FinTrust and find that proprietary models like o4-mini outperforms in most tasks such as safety while open-source models like DeepSeek-V3 have advantage in specific areas like industry-level fairness. For challenging task like fiduciary alignment and disclosure, all LLMs fall short, showing a significant gap in legal awareness. We believe that FinTrust can be a valuable benchmark for LLMs’ trustworthiness evaluation in finance domain.
Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation
PDF ↗In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a *static* to a *dynamic* paradigm. In this work, we conduct an in-depth analysis of existing *static* and *dynamic* benchmarks for evaluating LLMs. We first examine methods that enhance *static* benchmarks and identify their inherent limitations. We then highlight a critical gap—the lack of standardized criteria for evaluating *dynamic* benchmarks. Based on this observation, we propose a series of optimal design principles for *dynamic* benchmarking and analyze the limitations of existing *dynamic* benchmarks.This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models
PDF ↗Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment. Despite advances in defence measures for text and vision LLMs, effective safety-alignment strategies and audio-safety dataset specifically targeting LALMs are notably absent. Meanwhile defence measures based on Supervised Fine-tuning (SFT) struggle to address safety improvement while avoiding over-rejection issues, significantly compromising helpfulness. In this work, we propose an unsupervised safety-fine-tuning strategy as remedy that reshapes model’s representation space to enhance existing LALMs safety-alignment while balancing the risk of over-rejection. Our experiments, conducted across three generations of Qwen LALMs, demonstrate that our approach significantly improves LALMs safety under three modality input conditions (audio-text, text-only, and audio-only) while increasing over-rejection rate by only 0.88% on average. Warning: this paper contains harmful examples.
Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications
PDF ↗Personality is an important concept in psychology that reflects individual differences in thinking and behavior, and has significant applications across various fields. Most existing personality analysis methods address this issue at the bag level, treating the entire corpus gathered from one individual as a single unit for classification. However, this paradigm presents several challenges. From the data perspective, collecting a large corpus for each individual and performing comprehensive annotations pose significant difficulties in both data collection and labeling. On the application side, concentrating on classifying the entire corpus limits its applicability in more common single-instance scenarios. To address these issues, we propose a new task paradigm in text-based personality representation learning. Specifically, we construct a triplet personality trend comparison dataset to learn single-sentence personality embeddings with desirable metric properties. This approach removes the traditional constraints on data sources, facilitating dataset expansion, and can leverage the transfer capabilities of embeddings to easily adapt to various downstream tasks. Our experiments show that the learned embeddings significantly boost performance by a relative 10% across various applications, including personality detection, personality retrieval, and emotion translation prediction. The code and dataset are available at https://github.com/zjutangk/PTCD.
MusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completion
PDF ↗Open-world knowledge graph completion (KGC) aims to infer novel facts by enriching existing graphs with external knowledge sources while maintaining semantic consistency under the open-world assumption (OWA). Generation-based KGC methods leverage the inherent strengths of large language models (LLMs) in language understanding and creative problem-solving, making them promising approaches. However, they face limitations: (1) The unreliable external knowledge from LLMs can lead to hallucinations and undermine KGC reliability. (2) The lack of an automated and rational evaluation strategy for new facts under OWA results in the exclusion of some new but correct entities. In the paper, we propose MusKGC, a novel multi-source knowledge enhancement framework based on an LLM for KGC under OWA. We induce relation templates with entity type constraints to link structured knowledge with natural language, improving the comprehension of the LLM. Next, we combine intrinsic KG facts with reliable external knowledge to guide the LLM in accurately generating missing entities with supporting evidence. Lastly, we introduce a new evaluation strategy for factuality and consistency to validate accurate inferences of new facts, including unknown entities. Extensive experiments show that our proposed model achieves SOTA performance across benchmarks, and our evaluation strategy effectively assesses new facts under OWA.
Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still struggle to effectively manage large tool collections, researchers have begun exploring retrieval-based methods to pre-select the most relevant options, addressing input length and latency constraints. However, existing retrievers are often misaligned with tool-calling LLMs due to their separate training processes. This paper presents PORTS, a novel odds ratio preference optimization method for training retrievers aimed at tool selection. Using a perplexity-inspired preference signal from a frozen LLM, our approach fine-tunes a retriever to find helpful tools by optimizing the correlation between the selection probabilities and the downstream performances while jointly enforcing a contrastive semantic loss between documentation strings. The versatility of PORTS and its ability to significantly improve tool selection accuracy are demonstrated through extensive experiments on six datasets, two encoder models, and three LLMs with diverse prior knowledge. With low computational demands, our alignment process facilitates generalization to new queries and tools, proving valuable for practical applications with evolving toolsets.
Large language model (LLM) agents have demonstrated significant potential for addressing complex tasks through mechanisms such as chain-of-thought reasoning and tool invocation. However, current frameworks lack explicit supervision during the reasoning process, which may lead to error propagation across reasoning chains and hinder the optimization of intermediate decision-making stages. This paper introduces a novel framework, AgentPro, which enhances LLM agent performance by automated process supervision. AgentPro employs Monte Carlo Tree Search to automatically generate step-level annotations, and develops a process reward model based on these annotations to facilitate fine-grained quality assessment of reasoning. By employing a rejection sampling strategy, the LLM agent dynamically adjusts generation probability distributions to prevent the continuation of erroneous paths, thereby improving reasoning capabilities. Extensive experiments on four datasets indicate that our method significantly outperforms existing agent-based LLM methods (e.g., achieving a 6.32% increase in accuracy on the HotpotQA dataset), underscoring its proficiency in managing intricate reasoning chains.
Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first defines an importance criterion for tokens and then prunes the unimportant vision tokens during inference. However, in this paper, we show that the importance is not an ideal indicator to decide whether a token should be pruned. Surprisingly, it usually results in inferior performance than random token pruning and leading to incompatibility to efficient attention computation operators. Instead, we propose DART (Duplication-Aware Reduction of Tokens), which prunes tokens based on its duplication with other tokens, leading to significant and training-free acceleration. Concretely, DART selects a small subset of pivot tokens and then retains the tokens with low duplication to the pivots, ensuring minimal information loss during token pruning. Experiments demonstrate that DART can prune 88.9% vision tokens while maintaining comparable performance, leading to a 1.99\times and 2.99\times speed-up in total time and prefilling stage, respectively, with good compatibility to efficient attention operators.
When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. Despite much work on CoT prompting, it is unclear if reasoning verbalized in a CoT is faithful to the models’ parametric beliefs. We introduce a framework for measuring parametric faithfulness of generated reasoning and propose Faithfulness by Unlearning Reasoning steps (FUR), an instance of this framework. FUR erases information contained in reasoning steps from model parameters and measures faithfulness as the resulting effect on the model’s prediction. Our experiments with four LMs and five multi-choice question answering (MCQA) datasets show that FUR is frequently able to precisely change the underlying models’ prediction for a given instance by unlearning key steps, indicating when a CoT is parametrically faithful. Further analysis shows that CoTs generated by models post-unlearning support different answers, hinting at a deeper effect of unlearning.
Large language models (LLMs) can generate fluent text, raising concerns about misuse in online comments and academic writing, leading to issues like corpus pollution and copyright infringement. Existing LLM text detection methods often rely on features from the logit distribution of the input text. However, the distinction between the LLM-generated and human-written texts may rely on only a few tokens due to the short length or insufficient information in some texts, leading to minimal and hard-to-detect differences in logit distributions. To address this, we propose HALO, an LLM-based detection method that leverages external text corpora to evaluate the difference in the logit distribution of input text under retrieved human-written and LLM-rewritten contexts. HALO also complements basic detection features and can serve as a plug-and-play module to enhance existing detection methods. Extensive experiments on five public datasets with three widely-used source LLMs show that our proposed detection method achieves state-of-the-art performance in AUROC, both in cross-domain and domain-specific scenarios.
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
PDF ↗Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mechanism. We propose an automated pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training, helping the model focus on causal structures while mitigating noise and biases in attention scores. Experimental results on our proposed Spurious Token Game (STG) benchmark and multiple downstream tasks demonstrate that our approach effectively leverages causal knowledge for prediction and remains robust in OOD scenarios. The CAT achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks. Notably, the OOD performance of the Llama-3.1-8B model on STG_M increased from 64.5% to 90.5%, and Qwen’s OOD performance on the STG_H dataset improved from 25.4% to 55.9%. Implementation details can be found at https://github.com/Kairong-Han/CAT.
Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. Yet, a systematic evaluation of such risks is still lacking: existing benchmarks show coarse granularity, linguistic bias, and a neglect of multimodal privacy risks. To address these gaps, we introduce KoreaGEO, the first fine-grained, multimodal, and privacy-aware benchmark for geolocation, built on Korean street views. The benchmark covers four socio-spatial clusters and nine place types with rich contextual annotations and two captioning styles that simulate real-world privacy exposure. To evaluate mainstream VLMs, we design a three-path protocol spanning image-only, functional-caption, and high-risk-caption inputs, enabling systematic analysis of localization accuracy, spatial bias, and reasoning behavior. Results show that input modality exerts a stronger influence on localization precision and privacy exposure than model scale or architecture, with high-risk captions substantially boosting accuracy. Moreover, they highlight structural prediction biases toward core cities.
Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the “seesaw phenomenon”, where indiscriminate parameter updates yield progress on certain tasks at the expense of others. To address this challenge, we propose a novel Core Parameter Isolation Fine-Tuning (CPI-FT) framework. Specifically, we first independently fine-tune the LLM on each task to identify its core parameter regions by quantifying parameter update magnitudes. Tasks with similar core regions are then grouped based on region overlap, forming clusters for joint modeling. We further introduce a parameter fusion technique: for each task, core parameters from its individually fine-tuned model are directly transplanted into a unified backbone, while non-core parameters from different tasks are smoothly integrated via Spherical Linear Interpolation (SLERP), mitigating destructive interference. A lightweight, pipelined SFT training phase using mixed-task data is subsequently employed, while freezing core regions from prior tasks to prevent catastrophic forgetting. Extensive experiments on multiple public benchmarks demonstrate that our approach significantly alleviates task interference and forgetting, consistently outperforming vanilla multi-task and multi-stage fine-tuning baselines.
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
PDF ↗Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability to handle more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves them bottom-up using LLMs and TKG knowledge, and employs multi-path answer aggregation to improve fault tolerance. RTQA consists of three core components: the Temporal Question Decomposer, the Recursive Solver, and the Answer Aggregator. Experiments on MultiTQ and TimelineKGQA benchmarks demonstrate significant Hits@1 improvements in “Multiple” and “Complex” categories, outperforming state-of-the-art methods. Our code and data are available at https://github.com/zjukg/RTQA.
Personalized search systems in e-commerce platforms increasingly involve user interactions with AI assistants, where users consult about products, usage scenarios, and more. Leveraging consultation to personalize search services is trending. Existing methods typically rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but we observe that semantic similarity alone often fails to capture the true value of consultation for personalization. To address this, we propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value. Based on this, we introduce VAPS, a value-aware personalized search model that selectively incorporates high-value consultations through a consultation–user action interaction module and an explicit objective that aligns consultations with user actions. Experiments on both public and commercial datasets show that VAPS consistently outperforms baselines in both retrieval and ranking tasks. Codes are available at https://github.com/E-qin/VAPS.
Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. Previous defense methods correct poisoned image-caption pairs by matching a new caption for each image. However, the matching process solely relies on the global representations of images and captions, overlooking fine-grained features of visual and textual features. It may introduce incorrect image-caption pairs and detriment the CLIP pre-training. To address their limitations, we propose an Optimal Transport-based framework to reconstruct the image-caption pairs, named OTCCLIP. We involve a new optimal transport-based distance measure between fine-grained visual and textual feature sets and re-assign new captions based on the proposed optimal transport distance. Additionally, to further reduce the negative impact of mismatched pairs, we encourage the inter- and intra-modality fine-grained alignment by employing optimal transport-based objective functions. Our experiments demonstrate that OTCCLIP can successfully decrease the attack success rates of poisoning attacks to 0% in most cases. Also, compared to previous methods, OTCCLIPsignificantly improves CLIP’s zero-shot and linear probing performance trained on poisoned datasets.
Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.
The DIFF Transformer mitigates interference from irrelevant contexts by introducing a differential attention mechanism, thereby enhancing focus on critical tokens. However, this architecture suffers from two major limitations: first, its use of two independent attention matrices leads to numerical instability, and second, it lacks global context modeling, which is essential for identifying globally significant tokens. To address these challenges, we propose the DINT Transformer, which extends the DIFF Transformer by incorporating an integral mechanism. By computing global importance scores and integrating them into the attention matrix, the DINT Transformer not only improves overall numerical stability but also significantly enhances its ability to capture global dependencies. Experimental results demonstrate that the DINT Transformer achieves superior accuracy and robustness across various practical applications, including long-context language modeling and key information retrieval. These advancements establish the DINT Transformer as a highly effective and promising architecture.