Related papers: A$^2$Search: Ambiguity-Aware Question Answering wi…

Retrieval-Augmented Language Models (RALMs) have significantly improved performance in open-domain question answering (QA) by leveraging external knowledge. However, RALMs still struggle with unanswerable queries, where the retrieved…

Visual Question Answering (VQA) is a core task for evaluating the capabilities of Vision-Language Models (VLMs). Existing VQA benchmarks primarily feature clear and unambiguous image-question pairs, whereas real-world scenarios often…

Optimizing queries for Retrieval-Augmented Generation (RAG) systems poses a significant challenge, particularly across diverse modal indices. We introduce RL-QR, a novel annotation-free reinforcement learning framework for query rewriting…

Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, characterized by the "aha moment", in which the model manifest…

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…

Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong. We propose generating a single structured response that…

Recent Large Reasoning Models have achieved significant improvements in complex task-solving capabilities by allocating more computation at the inference stage with a "thinking longer" paradigm. Even as the foundational reasoning…

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from…

Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks…

Large language models (LLMs) can store a massive amount of knowledge, yet their potential to acquire new knowledge remains unknown. We propose a novel evaluation framework that evaluates this capability. This framework prompts LLMs to…

Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be validated using well-known evaluation metrics, the latter…

While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requirements, can be inflated when they are not compared to adequate…

This study delves into the capabilities and limitations of Large Language Models (LLMs) in the challenging domain of conditional question-answering. Utilizing the Conditional Question Answering (CQA) dataset and focusing on generative…

Building training-ready multi-hop question answering (QA) datasets that truly stress a model's retrieval and reasoning abilities remains highly challenging recently. While there have been a few recent evaluation datasets that capture the…

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning…

Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability…

Ambiguous questions are a challenge for Question Answering models, as they require answers that cover multiple interpretations of the original query. To this end, these models are required to generate long-form answers that often combine…

NL2SQL systems deployed in industry settings often encounter ambiguous or unanswerable queries, particularly in interactive scenarios with incomplete user clarification. Existing benchmarks typically assume a single source of ambiguity and…