With the increasing prevalence of recorded human speech, spoken language understanding (SLU) is essential for its efficient processing. In order to process the speech, it is commonly transcribed using automatic speech recognition technology. This speech-to-text transition introduces errors into the transcripts, which subsequently propagate to downstream NLP tasks, such as dialogue summarization. While it is known that transcript noise affects downstream tasks, a systematic approach to analyzing its effects across different noise severities and types has not been addressed. We propose a configurable framework for assessing task models in diverse noisy settings, and for examining the impact of transcript-cleaning techniques. The framework facilitates the investigation of task model behavior, which can in turn support the development of effective SLU solutions. We exemplify the utility of our framework on three SLU tasks and four task models, offering insights regarding the effect of transcript noise on tasks in general and models in particular. For instance, we find that task models can tolerate a certain level of noise, and are affected differently by the types of errors in the transcript.
Multi-Party Conversations (MPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets raise privacy concerns and often reflect platform-specific properties. For example, interactions between speakers may be limited due to rigid platform structures (e.g., threads, tree-like discussions), which yield overly simplistic interaction patterns (e.g., as a consequence of ``reply-to'' links). This work explores the feasibility of generating diverse MPCs with instruction-tuned Large Language Models (LLMs) by providing deterministic constraints such as dialogue structure and participants' stance. We investigate two complementary strategies of leveraging LLMs in this context: (i.) LLMs as MPC generators, where we task the LLM to generate a whole MPC at once and (ii.) LLMs as MPC parties, where the LLM generates one turn of the conversation at a time, provided the conversation history. We next introduce an analytical framework to evaluate compliance with the constraints, content quality, and interaction complexity for both strategies. Finally, we assess the quality of obtained MPCs via human annotation and LLM-as-a-judge evaluations. We find stark differences among LLMs, with only some being able to generate high-quality MPCs. We also find that turn-by-turn generation yields better conformance to constraints and higher linguistic variability than generating MPCs in one pass. Nonetheless, our structural and qualitative evaluation indicates that both generation strategies can yield high-quality MPCs.
Test-time compute scaling has emerged as a new axis along which to improve model accuracy, where additional computation is used at inference time to allow the model to think longer for more challenging problems. One promising approach for test-time compute scaling is search against a process reward model, where a model generates multiple potential candidates at each step of the search, and these partial trajectories are then scored by a separate reward model in order to guide the search process. The diversity of trajectories in the tree search process affects the accuracy of the search, since increasing diversity promotes more exploration. However, this diversity comes at a cost, as divergent trajectories have less KV sharing, which means they consume more memory and slow down the search process. Previous search methods either do not perform sufficient exploration, or else explore diverse trajectories but have high latency. We address this challenge by proposing Efficient Tree Search (ETS), which promotes KV sharing by pruning redundant trajectories while maintaining necessary diverse trajectories. ETS incorporates a linear programming cost model to promote KV cache sharing by penalizing the number of nodes retained, while incorporating a semantic coverage term into the cost model to ensure that we retain trajectories which are semantically different. We demonstrate how ETS can achieve 1.8$\times$ reduction in average KV cache size during the search process, leading to 1.4$\times$ increased throughput relative to prior state-of-the-art methods, with minimal accuracy degradation and without requiring any custom kernel implementation. Code is available at: https://github.com/SqueezeAILab/ETS.
Semi-supervised heterogeneous domain adaptation (SHDA) addresses learning across domains with distinct feature representations and distributions, where source samples are labeled while most target samples are unlabeled, with only a small fraction labeled. Moreover, there is no one-to-one correspondence between source and target samples. Although various SHDA methods have been developed to tackle this problem, the nature of the knowledge transferred across heterogeneous domains remains unclear. This paper delves into this question from an empirical perspective. We conduct extensive experiments on about 330 SHDA tasks, employing two supervised learning methods and seven representative SHDA methods. Surprisingly, our observations indicate that both the category and feature information of source samples do not significantly impact the performance of the target domain. Additionally, noise drawn from simple distributions, when used as source samples, may contain transferable knowledge. Based on this insight, we perform a series of experiments to uncover the underlying principles of transferable knowledge in SHDA. Specifically, we design a unified Knowledge Transfer Framework (KTF) for SHDA. Based on the KTF, we find that the transferable knowledge in SHDA primarily stems from the transferability and discriminability of the source domain. Consequently, ensuring those properties in source samples, regardless of their origin (e.g., image, text, noise), can enhance the effectiveness of knowledge transfer in SHDA tasks. The codes and datasets are available at https://github.com/yyyaoyuan/SHDA.
Cryo-electron tomography (cryoET) is a crucial technique for unveiling the structure of protein complexes. Automatically analyzing tomograms captured by cryoET is an essential step toward understanding cellular structures. In this paper, we introduce the 4th place solution from the CZII - CryoET Object Identification competition, which was organized to advance the development of automated tomogram analysis techniques. Our solution adopted a heatmap-based keypoint detection approach, utilizing an ensemble of two different types of 2.5D U-Net models with depth reduction. Despite its highly unified and simple architecture, our method achieved 4th place, demonstrating its effectiveness.
According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-quality Chain-of-Thought (COT) data. This data is then used to fine-tune the verification model, MM-Verifier. Additionally, we present a more efficient method for synthesizing MMCOT data, bridging the gap between text-based and multimodal reasoning. The synthesized data is used to fine-tune MM-Reasoner. Our MM-Verifier outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. Moreover, MM-Reasoner demonstrates strong effectiveness and scalability, with performance improving as data size increases. Finally, our approach achieves strong performance when combining MM-Reasoner and MM-Verifier, reaching an accuracy of 65.3 on MathVista, surpassing GPT-4o (63.8) with 12 rollouts.
Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these sequences. However, we find that by using minimal computational resources and without complex modifications to address video dynamics, an image-based model can be repurposed to outperform several specialised video captioning systems. Our adapted model demonstrates top tier performance on major benchmarks, ranking 2nd on MSRVTT and MSVD, and 3rd on VATEX. We transform it into a competitive video captioner by post training a typical image captioning model BLIP2 with only 6,000 video text pairs and simply concatenating frames (significantly fewer data than other methods), which use 2.5 to 144 million pairs. From a resource optimization perspective, this video captioning study focuses on three fundamental factors: optimizing model scale, maximizing data efficiency, and incorporating reinforcement learning. This extensive study demonstrates that a lightweight, image based adaptation strategy can rival state-of-the-art video captioning systems, offering a practical solution for low-resource scenarios.
Web crawl is a main source of large language models' (LLMs) pretraining data, but the majority of crawled web pages are discarded in pretraining due to low data quality. This paper presents Crawl4LLM, an efficient web crawling method that explores the web graph based on the preference of LLM pretraining. Specifically, it leverages the influence of a webpage in LLM pretraining as the priority score of the web crawler's scheduler, replacing the standard graph connectivity based priority. Our experiments on a web graph containing 900 million webpages from a commercial search engine's index demonstrate the efficiency of Crawl4LLM in obtaining high-quality pretraining data. With just 21% URLs crawled, LLMs pretrained on Crawl4LLM data reach the same downstream performances of previous crawls, significantly reducing the crawling waste and alleviating the burdens on websites. Our code is publicly available at https://github.com/cxcscmu/Crawl4LLM.
Anomaly detection (AD) is a fundamental task for time-series analytics with important implications for the downstream performance of many applications. In contrast to other domains where AD mainly focuses on point-based anomalies (i.e., outliers in standalone observations), AD for time series is also concerned with range-based anomalies (i.e., outliers spanning multiple observations). Nevertheless, it is common to use traditional point-based information retrieval measures, such as Precision, Recall, and F-score, to assess the quality of methods by thresholding the anomaly score to mark each point as an anomaly or not. However, mapping discrete labels into continuous data introduces unavoidable shortcomings, complicating the evaluation of range-based anomalies. Notably, the choice of evaluation measure may significantly bias the experimental outcome. Despite over six decades of attention, there has never been a large-scale systematic quantitative and qualitative analysis of time-series AD evaluation measures. This paper extensively evaluates quality measures for time-series AD to assess their robustness under noise, misalignments, and different anomaly cardinality ratios. Our results indicate that measures producing quality values independently of a threshold (i.e., AUC-ROC and AUC-PR) are more suitable for time-series AD. Motivated by this observation, we first extend the AUC-based measures to account for range-based anomalies. Then, we introduce a new family of parameter-free and threshold-independent measures, Volume Under the Surface (VUS), to evaluate methods while varying parameters. We also introduce two optimized implementations for VUS that reduce significantly the execution time of the initial implementation. Our findings demonstrate that our four measures are significantly more robust in assessing the quality of time-series AD methods.
Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudsters and users can greatly impact detection performance, since fraudsters tend to camouflage themselves by building more connections to benign users. Despite the promising performance of supervised GFD methods, the reliance on labels limits their applications to unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. To fill the gap, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel label-free heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily from node attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily among non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information while alleviating the feature-smooth effects of GNNs.Extensive experiments on 6 datasets demonstrate that HUGE significantly outperforms competitors, showcasing its effectiveness and robustness. The source code of HUGE is at https://github.com/CampanulaBells/HUGE-GAD.
We propose the Value Gradient Sampler (VGS), a trainable sampler based on the interpretation of sampling as discrete-time sequential decision-making. VGS generates samples from a given unnormalized density (i.e., energy) by drifting and diffusing randomly initialized particles. In VGS, finding the optimal drift is equivalent to solving an optimal control problem where the cost is the upper bound of the KL divergence between the target density and the samples. We employ value-based dynamic programming to solve this optimal control problem, which gives the gradient of the value function as the optimal drift vector. The connection to sequential decision making allows VGS to leverage extensively studied techniques in reinforcement learning, making VGS a fast, adaptive, and accurate sampler that achieves competitive results in various sampling benchmarks. Furthermore, VGS can replace MCMC in contrastive divergence training of energy-based models. We demonstrate the effectiveness of VGS in training accurate energy-based models in industrial anomaly detection applications.
Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open questions about real-world conversational patterns. To address this gap, we introduce REALTALK, a 21-day corpus of authentic messaging app dialogues, providing a direct benchmark against genuine human interactions. We first conduct a dataset analysis, focusing on EI attributes and persona consistency to understand the unique challenges posed by real-world dialogues. By comparing with LLM-generated conversations, we highlight key differences, including diverse emotional expressions and variations in persona stability that synthetic dialogues often fail to capture. Building on these insights, we introduce two benchmark tasks: (1) persona simulation where a model continues a conversation on behalf of a specific user given prior dialogue context; and (2) memory probing where a model answers targeted questions requiring long-term memory of past interactions. Our findings reveal that models struggle to simulate a user solely from dialogue history, while fine-tuning on specific user chats improves persona emulation. Additionally, existing models face significant challenges in recalling and leveraging long-term context within real-world conversations.
Graph Neural Networks (GNNs) have become a prominent approach for learning from graph-structured data. However, their effectiveness can be significantly compromised when the graph structure is suboptimal. To address this issue, Graph Structure Learning (GSL) has emerged as a promising technique that refines node connections adaptively. Nevertheless, we identify two key limitations in existing GSL methods: 1) Most methods primarily focus on node similarity to construct relationships, while overlooking the quality of node information. Blindly connecting low-quality nodes and aggregating their ambiguous information can degrade the performance of other nodes. 2) The constructed graph structures are often constrained to be symmetric, which may limit the model's flexibility and effectiveness. To overcome these limitations, we propose an Uncertainty-aware Graph Structure Learning (UnGSL) strategy. UnGSL estimates the uncertainty of node information and utilizes it to adjust the strength of directional connections, where the influence of nodes with high uncertainty is adaptively reduced. Importantly, UnGSL serves as a plug-in module that can be seamlessly integrated into existing GSL methods with minimal additional computational cost. In our experiments, we implement UnGSL into six representative GSL methods, demonstrating consistent performance improvements.
The advent of test-time scaling in large language models (LLMs), exemplified by OpenAI's o1 series, has advanced reasoning capabilities by scaling computational resource allocation during inference. While successors like QwQ, Deepseek-R1 (R1) and LIMO replicate these advancements, whether these models truly possess test-time scaling capabilities remains underexplored. This study found that longer CoTs of these o1-like models do not consistently enhance accuracy; in fact, correct solutions are often shorter than incorrect ones for the same questions. Further investigation shows this phenomenon is closely related to models' self-revision capabilities - longer CoTs contain more self-revisions, which often lead to performance degradation. We then compare sequential and parallel scaling strategies on QwQ, R1 and LIMO, finding that parallel scaling achieves better coverage and scalability. Based on these insights, we propose Shortest Majority Vote, a method that combines parallel scaling strategies with CoT length characteristics, significantly improving models' test-time scalability compared to conventional majority voting approaches.
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the next word. This division method provides more decision-making information at each step, enhancing downstream tasks, such as reward model learning. Moreover, our method does not require manual annotation. We demonstrate its effectiveness through experiments with AdaptiveStep-trained PRMs in mathematical reasoning and code generation tasks. Experimental results indicate that the outcome PRM achieves state-of-the-art Best-of-N performance, surpassing greedy search strategy with token-level value-guided decoding, while also reducing construction costs by over 30% compared to existing open-source PRMs. In addition, we provide a thorough analysis and case study on the PRM's performance, transferability, and generalization capabilities.
Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based recommendation (LLM4Rec) models under a sequential recommendation scenario, we found that whether these models understand the sequential information inherent in users' item interaction sequences has been largely overlooked. In this paper, we first demonstrate through a series of experiments that existing LLM4Rec models do not fully capture sequential information both during training and inference. Then, we propose a simple yet effective LLM-based sequential recommender, called LLM-SRec, a method that enhances the integration of sequential information into LLMs by distilling the user representations extracted from a pre-trained CF-SRec model into LLMs. Our extensive experiments show that LLM-SRec enhances LLMs' ability to understand users' item interaction sequences, ultimately leading to improved recommendation performance. Furthermore, unlike existing LLM4Rec models that require fine-tuning of LLMs, LLM-SRec achieves state-of-the-art performance by training only a few lightweight MLPs, highlighting its practicality in real-world applications. Our code is available at https://github.com/Sein-Kim/LLM-SRec.
Using Large Language Models (LLMs) for relevance assessments offers promising opportunities to improve Information Retrieval (IR), Natural Language Processing (NLP), and related fields. Indeed, LLMs hold the promise of allowing IR experimenters to build evaluation collections with a fraction of the manual human labor currently required. This could help with fresh topics on which there is still limited knowledge and could mitigate the challenges of evaluating ranking systems in low-resource scenarios, where it is challenging to find human annotators. Given the fast-paced recent developments in the domain, many questions concerning LLMs as assessors are yet to be answered. Among the aspects that require further investigation, we can list the impact of various components in a relevance judgment generation pipeline, such as the prompt used or the LLM chosen. This paper benchmarks and reports on the results of a large-scale automatic relevance judgment evaluation, the LLMJudge challenge at SIGIR 2024, where different relevance assessment approaches were proposed. In detail, we release and benchmark 42 LLM-generated labels of the TREC 2023 Deep Learning track relevance judgments produced by eight international teams who participated in the challenge. Given their diverse nature, these automatically generated relevance judgments can help the community not only investigate systematic biases caused by LLMs but also explore the effectiveness of ensemble models, analyze the trade-offs between different models and human assessors, and advance methodologies for improving automated evaluation techniques. The released resource is available at the following link: https://llm4eval.github.io/LLMJudge-benchmark/
This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Model (LLM) capabilities in data science. Recent related benchmarks have primarily focused on single tasks, easily obtainable ground truth, and straightforward evaluation metrics, which limits the scope of tasks that can be evaluated. In contrast, DataSciBench is constructed based on a more comprehensive and curated collection of natural and challenging prompts for uncertain ground truth and evaluation metrics. We develop a semi-automated pipeline for generating ground truth (GT) and validating evaluation metrics. This pipeline utilizes and implements an LLM-based self-consistency and human verification strategy to produce accurate GT by leveraging collected prompts, predefined task types, and aggregate functions (metrics). Furthermore, we propose an innovative Task - Function - Code (TFC) framework to assess each code execution outcome based on precisely defined metrics and programmatic rules. Our experimental framework involves testing 6 API-based models, 8 open-source general models, and 9 open-source code generation models using the diverse set of prompts we have gathered. This approach aims to provide a more comprehensive and rigorous evaluation of LLMs in data science, revealing their strengths and weaknesses. Experimental results demonstrate that API-based models outperform open-sourced models on all metrics and Deepseek-Coder-33B-Instruct achieves the highest score among open-sourced models. We release all code and data at https://github.com/THUDM/DataSciBench.
Conversational Product Search ( CPS ) systems interact with users via natural language to offer personalized and context-aware product lists. However, most existing research on CPS is limited to simulated conversations, due to the lack of a real CPS dataset driven by human-like language. Moreover, existing conversational datasets for e-commerce are constructed for a particular market or a particular language and thus can not support cross-market and multi-lingual usage. In this paper, we propose a CPS data collection protocol and create a new CPS dataset, called PSCon, which assists product search through conversations with human-like language. The dataset is collected by a coached human-human data collection protocol and is available for dual markets and two languages. By formulating the task of CPS, the dataset allows for comprehensive and in-depth research on six subtasks: user intent detection, keyword extraction, system action prediction, question selection, item ranking, and response generation. Moreover, we present a concise analysis of the dataset and propose a benchmark model on the proposed CPS dataset. Our proposed dataset and model will be helpful for facilitating future research on CPS.
Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline called CoT-Rec, which integrates two key Chain-of-Thought (CoT) processes -- user preference analysis and item perception analysis -- into LLM-powered recommendations, thereby enhancing the utilization of LLMs' reasoning abilities. CoT-Rec consists of two stages: (1) personalized information extraction, where user preferences and item perception are extracted, and (2) personalized information utilization, where this information is incorporated into the LLM-powered recommendation process. Experimental results demonstrate that CoT-Rec shows potential for improving LLM-powered recommendations. The implementation is publicly available at https://github.com/jhliu0807/CoT-Rec.