English
Related papers

Related papers: Reasoning Circuits: Few-shot Multihop Question Gen…

200 papers

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…

Computation and Language · Computer Science 2021-07-08 Kyungjae Lee , Seung-won Hwang , Sang-eun Han , Dohyeon Lee

Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…

Computation and Language · Computer Science 2022-10-27 Zhe Hu , Hou Pong Chan , Lifu Huang

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

Few-shot prompting and step-by-step reasoning have enhanced the capabilities of Large Language Models (LLMs) in tackling complex tasks including code generation. In this paper, we introduce a prompt selection and augmentation algorithm…

Robotics · Computer Science 2024-03-21 On Tai Wu , Frodo Kin Sun Chan , Zunhao Zhang , Yan Nei Law , Benny Drescher , Edmond Shiao Bun Lai

One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users' commands, a task trivial for humans due to their common sense. In this paper, we propose a zero-shot commonsense…

Artificial Intelligence · Computer Science 2021-09-20 Forough Arabshahi , Jennifer Lee , Antoine Bosselut , Yejin Choi , Tom Mitchell

Majority voting is considered an effective method to enhance chain-of-thought reasoning, as it selects the answer with the highest "self-consistency" among different reasoning paths (Wang et al., 2023). However, previous chain-of-thought…

Computation and Language · Computer Science 2025-05-19 Weiqin Wang , Yile Wang , Hui Huang

We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work, named PRover (Saha et al., 2020), performs such…

Computation and Language · Computer Science 2021-06-03 Swarnadeep Saha , Prateek Yadav , Mohit Bansal

The task of Critical Questions Generation (CQs-Gen) aims to foster critical thinking by enabling systems to generate questions that expose underlying assumptions and challenge the validity of argumentative reasoning structures. Despite…

Computation and Language · Computer Science 2025-09-24 Banca Calvo Figueras , Rodrigo Agerri

Generating accurate step-by-step reasoning is essential for Large Language Models (LLMs) to address complex problems and enhance robustness and interpretability. Despite the flux of research on developing advanced reasoning approaches,…

Computation and Language · Computer Science 2024-08-13 Shibo Hao , Yi Gu , Haotian Luo , Tianyang Liu , Xiyan Shao , Xinyuan Wang , Shuhua Xie , Haodi Ma , Adithya Samavedhi , Qiyue Gao , Zhen Wang , Zhiting Hu

KBQA is a task that requires to answer questions by using semantic structured information in knowledge base. Previous work in this area has been restricted due to the lack of large semantic parsing dataset and the exponential growth of…

Computation and Language · Computer Science 2022-01-28 Meihao Fan , Lei Zhang , Siyao Xiao , Yuru Liang

Multi-hop question answering is a knowledge-intensive complex problem. Large Language Models (LLMs) use their Chain of Thoughts (CoT) capability to reason complex problems step by step, and retrieval-augmentation can effectively alleviate…

Computation and Language · Computer Science 2024-04-24 Li Jiapeng , Liu Runze , Li Yabo , Zhou Tong , Li Mingling , Chen Xiang

Chain-of-thought prompting has demonstrated great success in facilitating the reasoning abilities of large language models. In this work, we explore how these enhanced reasoning abilities can be exploited to improve the robustness of large…

Computation and Language · Computer Science 2025-04-30 Wenxiao Wang , Parsa Hosseini , Soheil Feizi

While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous…

Computation and Language · Computer Science 2026-04-28 Keshav Ramji , Tahira Naseem , Ramón Fernandez Astudillo

This paper introduces Omne-R1, a novel approach designed to enhance multi-hop question answering capabilities on schema-free knowledge graphs by integrating advanced reasoning models. Our method employs a multi-stage training workflow,…

Computation and Language · Computer Science 2025-08-26 Boyuan Liu , Feng Ji , Jiayan Nan , Han Zhao , Weiling Chen , Shihao Xu , Xing Zhou

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and…

Computation and Language · Computer Science 2023-08-22 Pengbo Hu , Ji Qi , Xingyu Li , Hong Li , Xinqi Wang , Bing Quan , Ruiyu Wang , Yi Zhou

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…

Computation and Language · Computer Science 2024-06-21 Yuval Shalev , Amir Feder , Ariel Goldstein

Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a…

Computation and Language · Computer Science 2023-07-28 Angela Ramirez , Karik Agarwal , Juraj Juraska , Utkarsh Garg , Marilyn A. Walker

Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work…

Computation and Language · Computer Science 2021-07-08 Ernie Chang , Xiaoyu Shen , Hui-Syuan Yeh , Vera Demberg

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest…

Computation and Language · Computer Science 2026-03-25 Jiajun Zhang , Shijia Luo , Ruikang Zhang , Qi Su