English
Related papers

Related papers: Prompt Architecture Determines Reasoning Quality: …

200 papers

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Computation and Language · Computer Science 2023-04-03 Huan Ma , Changqing Zhang , Yatao Bian , Lemao Liu , Zhirui Zhang , Peilin Zhao , Shu Zhang , Huazhu Fu , Qinghua Hu , Bingzhe Wu

Reasoning in the real world is not divorced from situations. How to capture the present knowledge from surrounding situations and perform reasoning accordingly is crucial and challenging for machine intelligence. This paper introduces a new…

Artificial Intelligence · Computer Science 2024-05-17 Bo Wu , Shoubin Yu , Zhenfang Chen , Joshua B Tenenbaum , Chuang Gan

Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings: model responses are assumed to be instantaneous, and the context of a request is presumed to be immutable over the…

Computation and Language · Computer Science 2025-10-17 Tsung-Han Wu , Mihran Miroyan , David M. Chan , Trevor Darrell , Narges Norouzi , Joseph E. Gonzalez

This study evaluates causal reasoning in large language models (LLMs) using 99 clinically grounded laboratory test scenarios aligned with Pearl's Ladder of Causation: association, intervention, and counterfactual reasoning. We examined…

Artificial Intelligence · Computer Science 2025-09-23 Balu Bhasuran , Mattia Prosperi , Karim Hanna , John Petrilli , Caretia JeLayne Washington , Zhe He

Large Language Model interfaces are increasingly verbose, exposing intermediate reasoning traces alongside final answers. Traces are framed as transparency mechanisms, yet it is unclear how people use them to solve problems. We report a…

Human-Computer Interaction · Computer Science 2026-05-26 Daniela Fernandes , Daniel Buschek , Lev Tankelevitch , Thomas Kosch , Robin Welsch

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Linjie Li , Mahtab Bigverdi , Jiawei Gu , Zixian Ma , Yinuo Yang , Ziang Li , Yejin Choi , Ranjay Krishna

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning…

Computation and Language · Computer Science 2026-04-21 Di Wu , Devendra Singh Sachan , Wen-tau Yih , Mingda Chen

Large Language Model agents increasingly operate external systems through programmatic interfaces, yet practitioners lack empirical guidance on how to structure the context these agents consume. Using SQL generation as a proxy for…

Computation and Language · Computer Science 2026-02-13 Damon McMillan

We study the ability of language models to reason about appropriate information disclosure - a central aspect of the evolving field of agentic privacy. Whereas previous works have focused on evaluating a model's ability to align with human…

Artificial Intelligence · Computer Science 2026-01-28 Ren Yi , Octavian Suciu , Adria Gascon , Sarah Meiklejohn , Eugene Bagdasarian , Marco Gruteser

Language models can be prompted to reason through problems in a manner that significantly improves performance. However, \textit{why} such prompting improves performance is unclear. Recent work showed that using logically \textit{invalid}…

Artificial Intelligence · Computer Science 2023-07-25 Rylan Schaeffer , Kateryna Pistunova , Samar Khanna , Sarthak Consul , Sanmi Koyejo

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

How carefully and unambiguously a question is phrased has a profound impact on the quality of the response, for Language Models (LMs) as well as people. While model capabilities continue to advance, the interplay between grounding context…

Computation and Language · Computer Science 2026-03-06 Michael Majurski , Cynthia Matuszek

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Machine Learning · Computer Science 2025-10-28 Taeyoun Kim , Fahim Tajwar , Aditi Raghunathan , Aviral Kumar

Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performance by sampling more reasoning chains when saturated. To…

Computation and Language · Computer Science 2024-06-06 Weisen Jiang , Han Shi , Longhui Yu , Zhengying Liu , Yu Zhang , Zhenguo Li , James T. Kwok

We present a simulation-based evaluation of the Inference Headroom Ratio (IHR), a dimensionless diagnostic quantity for characterizing inference stability in constrained decision systems. IHR formalizes the relationship between a system's…

Artificial Intelligence · Computer Science 2026-04-23 Robert Reinertsen

Enhancing the reasoning capabilities of language models (LMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making where existing Chain-of-Thought (CoT) approaches struggle with consistency and…

Computation and Language · Computer Science 2025-08-21 Siheng Xiong , Ali Payani , Yuan Yang , Faramarz Fekri

Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models boasting extended context capabilities, with some…

Computation and Language · Computer Science 2024-07-16 Amanda Dsouza , Christopher Glaze , Changho Shin , Frederic Sala

Implicit Sentiment Analysis (ISA) aims to infer sentiment that is implied rather than explicitly stated, requiring models to perform deeper reasoning over subtle contextual cues. While recent prompting-based methods using Large Language…

Computation and Language · Computer Science 2025-07-02 Jing Ren , Wenhao Zhou , Bowen Li , Mujie Liu , Nguyen Linh Dan Le , Jiade Cen , Liping Chen , Ziqi Xu , Xiwei Xu , Xiaodong Li

Recent Large Reasoning Models (LRMs) have achieved remarkable progress on task-specific benchmarks, yet their evaluation methods remain constrained by isolated problem-solving paradigms. Existing benchmarks predominantly assess…

Computation and Language · Computer Science 2025-07-16 Zhuoshi Pan , Qizhi Pei , Yu Li , Qiyao Sun , Zinan Tang , H. Vicky Zhao , Conghui He , Lijun Wu

Prompting strategies affect LLM reasoning performance, but their role in chart-based QA remains underexplored. We present a systematic evaluation of four widely used prompting paradigms (Zero-Shot, Few-Shot, Zero-Shot Chain-of-Thought, and…

Computation and Language · Computer Science 2026-03-25 Ruthuparna Naikar , Ying Zhu