paper-with-me

Papers

Certified Deductive Reasoning with Language Models

2023-06-06 · Gabriel Poesia, Kanishk Gandhi, Eric Zelikman, Noah D. Goodman

Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logically unsound or inconsistent. This is a major issue when reliable reasoning traces are needed, such when fine-tuning on model-generated reasoning for self-improvement. To tackle these issues, we introduce a class of tools for language models called \emph{guides}, that use state and incremental constraints to guide generation. A guide can be invoked by the model to constrain its own generation to a set of valid statements given by the tool. In turn, the model's choices can change the guide's state. We show how a general system for logical reasoning can be used as a guide, which we call \textsc{LogicGuide}. Given a reasoning problem in natural language, a model can formalize its assumptions for \textsc{LogicGuide} and guarantee that its step-by-step reasoning is sound. In experiments on PrOntoQA, ProofWriter and Syllogism Validity datasets, \textsc{LogicGuide} significantly improves the performance of GPT-3, GPT-3.5 Turbo and LLaMA (accuracy gains up to 35\%), while drastically reducing \emph{content effects} -- the interference between unwanted prior assumptions and reasoning, which humans and language models suffer from. We then explore bootstrapping GPT-3.5 Turbo and LLaMA using their own reasoning traces. We find that LogicGuide is critical: by training only on certified self-generated reasoning, models can self-improve, avoiding learning from their own hallucinations. Moreover, bootstrapped models enjoy significant boosts on ReClor, a challenging real-world reasoning dataset, even when not relying on formalization at inference time.

📄 PDF Abstract BibTeX arXiv:2306.04031

Code (1)

gpoesia/certified-reasoning

Tasks

Logical Reasoningvalid

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis

2026-02-03 · Xiao Sun, Yuming Yang, Junnan Zhu, Jiang Zhong 외 arxiv

Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric assessment, their clinical utility is severely constrained by b…

Reinforcement Learning

Deductive Verification of Chain-of-Thought Reasoning

2023-06-06 · NeurIPS 2023 11 · Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang 외

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on i…

Logical Reasoning

Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs

2024-07-31 · Kewei Cheng, Jingfeng Yang, Haoming Jiang, Zhengyang Wang 외

Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously dif…

counterfactualCounterfactual Reasoning

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

2025-01-20 · Wentao Wan, Zhuojie Yang, Yongcan Chen, Chenglin Luo 외

Deductive reasoning is a crucial logical capability that assists us in solving complex problems based on existing knowledge. Although augmented by Chain-of-Thought prompts, Large Language Models (LLMs) might not follow t…

Can Pretrained Language Models (Yet) Reason Deductively?

2022-10-12 · Zhangdie Yuan, Songbo Hu, Ivan Vulić, Anna Korhonen 외

Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks. Their good performance has led the community to beli…