Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling

• URL: http://arxiv.org/abs/2412.14860v1
• Date: Thu, 19 Dec 2024 13:55:48 GMT
• Title: Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
• Authors: Junyi Li, Hwee Tou Ng,
• Abstract summary: Large language models (LLMs) are prone to hallucination and producing factually incorrect information. We propose a novel framework, called Think&Cite, and formulate attributed text generation as a multi-step reasoning problem integrated with search.
• Score: 63.98194996746229
• License:
• Abstract: Despite their outstanding capabilities, large language models (LLMs) are prone to hallucination and producing factually incorrect information. This challenge has spurred efforts in attributed text generation, which prompts LLMs to generate content with supporting evidence. In this paper, we propose a novel framework, called Think&Cite, and formulate attributed text generation as a multi-step reasoning problem integrated with search. Specifically, we propose Self-Guided Monte Carlo Tree Search (SG-MCTS), which capitalizes on the self-reflection capability of LLMs to reflect on the intermediate states of MCTS for guiding the tree expansion process. To provide reliable and comprehensive feedback, we introduce Progress Reward Models to measure the progress of tree search from the root to the current state from two aspects, i.e., generation and attribution progress. We conduct extensive experiments on three datasets and the results show that our approach significantly outperforms baseline approaches.

Related papers

• Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking [124.69672273754144]
  HaluSearch is a novel framework that incorporates tree search-based algorithms. It frames text generation as a step-by-step reasoning process. We introduce a hierarchical thinking system switch mechanism inspired by the dual process theory in cognitive science.
  arXiv  Detail & Related papers  (2025-01-02T15:36:50Z)
• RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement [85.08223786819532]
  Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. We propose textbfRAG-Star, a novel RAG approach that integrates retrieved information to guide the tree-based deliberative reasoning process. Our experiments involving Llama-3.1-8B-Instruct and GPT-4o demonstrate that RAG-Star significantly outperforms previous RAG and reasoning methods.
  arXiv  Detail & Related papers  (2024-12-17T13:05:36Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering [9.86691461253151]
  We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of large language models (LLMs) Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. We present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.
  arXiv  Detail & Related papers  (2024-05-28T09:12:44Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection [13.608076739368949]
  We introduce a novel framework that harnesses the potential of large-scale pre-trained language models. Our framework processes the output of a typical few-shot chain-of-thought prompt, assesses the correctness of the response, scrutinizes the answer, and ultimately produces a new solution.
  arXiv  Detail & Related papers  (2023-10-08T06:36:26Z)
• Enabling Large Language Models to Generate Text with Citations [37.64884969997378]
  Large language models (LLMs) have emerged as a widely-used tool for information seeking. Our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability. We propose ALCE, the first benchmark for Automatic LLMs' Citation Evaluation.
  arXiv  Detail & Related papers  (2023-05-24T01:53:49Z)
• Writing your own book: A method for going from closed to open book QA to improve robustness and performance of smaller LLMs [0.9421843976231371]
  We introduce two novel methods to enhance the performance of large language models (LLMs) in question-answering tasks. Tree-Search is a sampling technique created to extract diverse information from an LLM for a given prompt. Self-contextualizing QA leverages Tree-Search to enable the model to create its own context using a wide range of information relevant to the prompt.
  arXiv  Detail & Related papers  (2023-05-18T22:47:06Z)
• Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner [56.08919422452905]
  We propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR) Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. We outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
  arXiv  Detail & Related papers  (2022-05-18T21:52:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.