Conformal Language Model Reasoning with Coherent Factuality

• URL: http://arxiv.org/abs/2505.17126v1
• Date: Wed, 21 May 2025 22:40:51 GMT
• Title: Conformal Language Model Reasoning with Coherent Factuality
• Authors: Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji, Aaron Roth, Surbhi Goel,
• Abstract summary: We develop a conformal-prediction-based method to guarantee coherent factuality for language model outputs.<n>We evaluate our method on mathematical reasoning problems from the MATH and FELM datasets.
• Score: 15.041904552455915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factuality" of claims decomposed from a language model generation and applying conformal prediction techniques to filter out those claims that are not factual. This can be effective for tasks such as information retrieval, where constituent claims may be evaluated in isolation for factuality, but is not appropriate for reasoning tasks, as steps of a logical argument can be evaluated for correctness only within the context of the claims that precede them. To capture this, we define "coherent factuality" and develop a conformal-prediction-based method to guarantee coherent factuality for language model outputs. Our approach applies split conformal prediction to subgraphs within a "deducibility" graph" that represents the steps of a reasoning problem. We evaluate our method on mathematical reasoning problems from the MATH and FELM datasets and find that our algorithm consistently produces correct and substantiated orderings of claims, achieving coherent factuality across target coverage levels. Moreover, we achieve 90% factuality on our stricter definition while retaining 80% or more of the original claims, highlighting the utility of our deducibility-graph-guided approach.

Related papers

• Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens [14.78605805191225]
  We investigate how the semantics of intermediate tokens-often anthropomorphized as "thoughts" or reasoning traces-actually influence model performance.<n>We show that despite significant improvements on the solution-only baseline, models trained on entirely correct traces still produce invalid reasoning traces when arriving at correct solutions.
  arXiv  Detail & Related papers  (2025-05-19T23:29:23Z)
• Search-Based Correction of Reasoning Chains for Language Models [72.61861891295302]
  Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs)<n>We introduce a new self-correction framework that augments each reasoning step in a CoT with a latent variable indicating its veracity.<n>We also introduce Search Corrector, a discrete search algorithm over-valued veracity assignments.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation [0.0]
  We explore uncertainty estimation as a proxy for correctness in LLM-generated code.<n>We adapt two state-of-the-art techniques from natural language generation to the domain of code generation.<n>Our findings indicate a strong correlation between the uncertainty computed through these techniques and correctness.
  arXiv  Detail & Related papers  (2025-02-17T10:03:01Z)
• Towards Effective Extraction and Evaluation of Factual Claims [1.8262547855491458]
  A common strategy for fact-checking long-form content generated by Large Language Models (LLMs) is extracting simple claims that can be verified independently.<n>We propose a framework for evaluating claim extraction in the context of fact-checking along with automated, scalable, and replicable methods for applying this framework.<n>We also introduce Claimify, an LLM-based claim extraction method, and demonstrate that it outperforms existing methods under our evaluation framework.
  arXiv  Detail & Related papers  (2025-02-15T16:58:05Z)
• Learning Latent Graph Structures and their Uncertainty [63.95971478893842]
  Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy. As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task.
  arXiv  Detail & Related papers  (2024-05-30T10:49:22Z)
• Unsupervised Pretraining for Fact Verification by Language Model Distillation [4.504050940874427]
  We propose SFAVEL (Self-supervised Fact Verification via Language Model Distillation), a novel unsupervised pretraining framework. It distils self-supervised features into high-quality claim-fact alignments without the need for annotations. This is enabled by a novel contrastive loss function that encourages features to attain high-quality claim and evidence alignments.
  arXiv  Detail & Related papers  (2023-09-28T15:53:44Z)
• Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization [56.94741578760294]
  We propose the task of fine-grained inconsistency detection, the goal of which is to predict the fine-grained types of factual errors in a summary. Motivated by how humans inspect factual inconsistency in summaries, we propose an interpretable fine-grained inconsistency detection model, FineGrainFact.
  arXiv  Detail & Related papers  (2023-05-23T22:11:47Z)
• ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning [63.77667876176978]
  Large language models show improved downstream task interpretability when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness is difficult. We present ROS, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics.
  arXiv  Detail & Related papers  (2022-12-15T15:52:39Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction [54.06292969184476]
  We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Our approach employs semantic loss which captures the precise meaning of a logical sentence. With a focus on low-data regimes, we show that semantic loss outperforms the baselines by a wide margin.
  arXiv  Detail & Related papers  (2021-03-20T00:16:29Z)
• Generating Fact Checking Explanations [52.879658637466605]
  A crucial piece of the puzzle that is still missing is to understand how to automate the most elaborate part of the process. This paper provides the first study of how these explanations can be generated automatically based on available claim context. Our results indicate that optimising both objectives at the same time, rather than training them separately, improves the performance of a fact checking system.
  arXiv  Detail & Related papers  (2020-04-13T05:23:25Z)

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.