Related papers: MGR: Multi-generator Based Rationalization

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the…

Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance…

Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a document. Often though, they result in a tradeoff between noisy…

Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we identify a systematic lack of emphasis on more challenging questions in existing methods from…

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the…

Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages using several reasoning steps. Chain-of-thought rationale generation has been…

In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically,…

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge…

Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve unstructured chunks…

Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…

In modern multi-stage recommendation systems, reranking plays a critical role by modeling contextual information. Due to inherent challenges such as the combinatorial space complexity, an increasing number of methods adopt the generative…

Generating explanation to explain its behavior is an essential capability for a robotic teammate. Explanations help human partners better understand the situation and maintain trust of their teammates. Prior work on robot generating…

The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate…

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional…

Multi-choice Machine Reading Comprehension (MRC) is a challenging extension of Natural Language Processing (NLP) that requires the ability to comprehend the semantics and logical relationships between entities in a given text. The MRC task…

Mathematical formulas are the crystallization of human wisdom in exploring the laws of nature for thousands of years. Describing the complex laws of nature with a concise mathematical formula is a constant pursuit of scientists and a great…

The idea of adversarial learning of regularization functionals has recently been introduced in the wider context of inverse problems. The intuition behind this method is the realization that it is not only necessary to learn the basic…