18 accepted papers
LLM agents powered by retrieval and RAG are increasingly prevalent across research and applications. Embedding models play a critical role in these systems, particularly in embedding-based retrieval. However, current benchmarks for embeddings, such as MTEB, remain focused on general-purpose scenario…
Memory is a core capability of autonomous agents, yet existing benchmarks evaluate it primarily in constrained settings such as short dialogues or synthetic tasks, failing to reflect realistic agent deployments. We present \textbf{Memoria-Bench}, a benchmark for evaluating agent memory grounded in c…
Conditional Semantic Textual Similarity (C-STS) measures the semantic proximity between text segments under a specific condition, thereby overcoming the ambiguity inherent in traditional STS. However, existing methods are largely confined to discriminative models, failing to fully integrate recent b…
Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end build/test success, obscuring where and why agents succeed…
Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained models causes performance degradation due to train-inference distribution mismatch, and (2) a capability gap, where model…
Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning by organizing fragmented knowledge into explicitly structured graphs. Prior efforts have been made to improve either graph construction or graph retrieval in isolation, yielding subopt…
When carefully optimized by human experts, naive prompts can significantly enhance the task performance of large language models (LLMs). However, such expert-driven prompt optimizations are resource-intensive. To address this, some studies have proposed Automatic Prompt Optimization (APO), which ref…
While Chain of Thought (CoT) prompting approaches have significantly consolidated the reasoning capabilities of large language models (LLMs), they still face limitations that require extensive human effort or have performance needs to be improved. Existing endeavors have focused on bridging these ga…
Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on “huge” databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To…
Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role’s pre-defined ability limits. Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-playing in instr…
Role-playing agents (RPAs) are garnering increasing interests as a novel form of conversational AI. While previous research has predominantly concentrated on their ability to portray specified characters, we argue from a user-centered perspective that RPAs’ capability to advance the plot requires su…
Evaluating the ability of large language models (LLMs) to process lengthy contexts is critical, especially for retrieving query-relevant information embedded within them. We introduce Sequential-NIAH, a benchmark specifically designed to evaluate the capability of LLMs to extract sequential informat
Role-Playing Agents (RPAs) have shown remarkable performance in various applications, yet they often struggle to recognize and appropriately respond to hard queries that conflict with their role-play knowledge. To investigate RPAs’ performance when faced with different types of conflicting requests,…
Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF). Despite its promising ef…
Extending from unimodal to multimodal is a critical challenge for unsupervised domain adaptation (UDA). Two major problems emerge in unsupervised multimodal domain adaptation: domain adaptation and modality alignment. An intuitive way to handle these two problems is to fulfill these tasks in two sep…
In the scenario of unsupervised extractive summarization, learning high-quality sentence representations is essential to select salient sentences from the input document. Previous studies focus more on employing statistical approaches or pre-trained language models (PLMs) to extract sentence embeddi…
Multimodal headline utilizes both video frames and transcripts to generate the natural language title of the videos. Due to a lack of large-scale, manually annotated data, the task of annotating grounded headlines for video is labor intensive and impractical. Previous researches on pre-trained langu…
In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multipleevents may lie in one document (multi-event issue). In this paper, we argue that the relation information of event arguments is of greatsignificance for addressing the a…