Related papers: DeepThink: Aligning Language Models with Domain-Sp…

Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved…

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high…

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…

Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to individual learners, while existing RAG systems fall short…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various applications. However, their use as writing assistants in specialized domains like finance, medicine, and law is often hampered by a lack of deep…

Many AI systems focus solely on providing solutions or explaining outcomes. However, complex tasks like research and strategic thinking often benefit from a more comprehensive approach to augmenting the thinking process rather than…

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal…

Controlling the text generated by language models and customizing the content has been a long-standing challenge. Existing prompting techniques proposed in pursuit of providing control are task-specific and lack generality; this provides…

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of relevant information…

Assessing ways in which Language Models can reduce their hallucinations and improve the outputs' quality is crucial to ensure their large-scale use. However, methods such as fine-tuning on domain-specific data or the training of a separate…

In this paper, we introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language model (LLM). Our approach constructs a structured thinking…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software…

Conversations with LMs involve two participants: a human user leading the conversation, and an LM assistant responding to the user's request. To satisfy this specific role, LMs are post-trained to be helpful assistants -- optimized to…

Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…

Electronic design engineers often struggle to efficiently access relevant information for tasks like design verification and technology development. While large language models (LLMs) can enhance productivity as conversational agents,…