Related papers: Knowing When to Ask: Segment-Level Credit Assignme…

As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibitive, hindering rapid development. Despite the availability of…

Automatic video captioning aims for a holistic visual scene understanding. It requires a mechanism for capturing temporal context in video frames and the ability to comprehend the actions and associations of objects in a given timeframe.…

The integration of large language models (LLMs) and search engines represents a significant evolution in knowledge acquisition methodologies. However, determining the knowledge that an LLM already possesses and the knowledge that requires…

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and…

We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools…

The integration of tools has extended the capabilities of language models (LMs) beyond vanilla text generation to versatile scenarios. However, tool-augmented language models (TaLMs) often assume 'perfect' information access and tool…

Prior work shows that program-aided reasoning, in which large language models (LLMs) are combined with programs written in programming languages such as Python, can significantly improve accuracy on various reasoning tasks. However, while…

Reward models (RMs) are crucial for aligning large language models (LLMs) with diverse cultures. Consequently, evaluating their cultural awareness is essential for further advancing global alignment of LLMs. However, existing RM evaluations…

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through…

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for financial documents that include tabular and textual data.…

Many tasks require learned models to strategically gather relevant information over multiple rounds of interaction before actually acting on a task. Strategic information gathering requires models to know not only how to effectively acquire…

Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies from interaction…

Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the…

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…

Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary…

Large language models are increasingly used to support high-stakes decisions, potentially influencing who is granted bail or receives a loan. Naive chain-of-thought sampling can improve average decision accuracy, but has also been shown to…