Related papers: Draft-Refine-Optimize: Self-Evolved Learning for N…

Multi-modal retrieval-augmented Question Answering (MRAQA), integrating text and images, has gained significant attention in information retrieval (IR) and natural language processing (NLP). Traditional ranking methods rely on small…

Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better…

Summarization of long-form text data is a problem especially pertinent in knowledge economy jobs such as medicine and finance, that require continuously remaining informed on a sophisticated and evolving body of knowledge. As such,…

Achieving human-like reasoning capabilities in Multimodal Large Language Models (MLLMs) has long been a goal. Current methods primarily focus on synthesizing positive rationales, typically relying on manual annotations or complex systems.…

The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and…

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and…

Large language models (LLMs), especially Explicit Long Chain-of-Thought (CoT) reasoning models like DeepSeek-R1 and QWQ, have demonstrated powerful reasoning capabilities, achieving impressive performance in commonsense reasoning and…

Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc methods…

Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

We introduce the \textit{Extract-Refine-Retrieve-Read} (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the…

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool…

The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical in the Text-to-SQL task, where the scarcity, limited…

Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel…

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been…

Querying knowledge bases using ontologies is usually performed using dedicated query languages, question-answering systems, or visual query editors for Knowledge Graphs. We propose a novel approach that enables users to query the knowledge…

Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge…