paper-with-me

홈 › Papers

DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs

2024-06-11 · Haishuo Fang, Xiaodan Zhu, Iryna Gurevych

Answering Questions over Knowledge Graphs (KGQA) is key to well-functioning autonomous language agents in various real-life applications. To improve the neural-symbolic reasoning capabilities of language agents powered by Large Language Models (LLMs) in KGQA, we propose the DecompositionAlignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism: high-level iterative task decomposition and low-level task grounding. Importantly, DARA can be efficiently trained with a small number of high-quality reasoning trajectories. Our experimental results demonstrate that DARA fine-tuned on LLMs (e.g. Llama-2-7B, Mistral) outperforms both in-context learning-based agents with GPT-4 and alternative fine-tuned agents, across different benchmarks in zero-shot evaluation, making such models more accessible for real-life applications. We also show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA.

📄 PDF Abstract BibTeX arXiv:2406.07080

Code (1)

UKPLab/acl2024-DARA 공식 구현

Tasks

In-Context LearningKnowledge GraphsQuestion Answering

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning

2026-04-12 · Cheng-Yen Li, Xuanjun Chen, Claire Lin, Wei-Yu Chen 외 arxiv

Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external so…

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering

2026-01-27 · Fangan Dong, Zuming Yan, Xuri Ge, Zhiwei Xu 외 arxiv

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limitin…

DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding

2024-05-10 · Ting Liu, Xuyang Liu, Siteng Huang, Honggang Chen 외

Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved performance, but also introduced a significa…

RelationSpatial ReasoningTransfer LearningVisual Grounding

TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction

2025-11-16 · Jie Zhang, Bo Tang, Wanzi Shao, Wenqiang Wei 외 arxiv

Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in res…

Reinforcement Learning

VERDI: VLM-Embedded Reasoning for Autonomous Driving

2025-05-21 · Bowen Feng, Zhiting Mei, Baiang Li, Julian Ost 외

While autonomous driving (AD) stacks struggle with decision making under partial observability and real-world complexity, human drivers are capable of commonsense reasoning to make near-optimal decisions with limited inf…

Autonomous DrivingTrajectory Planning