Pith. sign in

REVIEW 8 cited by

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.09267 v2 pith:WB7JHNSX submitted 2024-02-14 cs.CL cs.AI

classification cs.CLcs.AI
keywords factualityself-evaluationhallucinationsmodelself-alignmentfactualknowledgellms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowledge. To address these hallucinations, current approaches typically necessitate high-quality human factuality annotations. In this work, we explore Self-Alignment for Factuality, where we leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. Specifically, we incorporate Self-Eval, a self-evaluation component, to prompt an LLM to validate the factuality of its own generated responses solely based on its internal knowledge. Additionally, we design Self-Knowledge Tuning (SK-Tuning) to augment the LLM's self-evaluation ability by improving the model's confidence estimation and calibration. We then utilize these self-annotated responses to fine-tune the model via Direct Preference Optimization algorithm. We show that the proposed self-alignment approach substantially enhances factual accuracy over Llama family models across three key knowledge-intensive tasks on TruthfulQA and BioGEN.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. URPO: A Unified Reward & Policy Optimization Framework for Large Language Models

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A seven-billion-parameter model trained with one unified GRPO loop improves instruction following, reasoning, and reward modeling at the same time.

  2. Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Pre-trained multivariate time-series imputation models frequently return values that violate known relations between variables, and a diffusion-based score can detect and filter these errors.

  3. Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis

    cs.CL 2025-05 conditional novelty 6.0 of 10

    PhantomCircuit traces knowledge overshadowing to attention circuits during training and prunes circuit edges to recover the overshadowed answer.

  4. Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    The abstract claims a new local search framework for code generation, but the manuscript body is a different mathematics paper.

  5. A Mathematical Theory of Discursive Networks

    cs.CL 2025-07 reject novelty 3.0 of 10

    A two-state Markov model of error propagation suggests that small amounts of cross-agent peer review can flip a network of fallible language models from a falsehood-dominant to a truth-dominant state.

  6. A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models

    cs.IR 2025-07 reject novelty 3.0 of 10

    A survey claims proactive defenses against LLM misinformation outperform post-hoc detection by up to 63%, but no meta-analysis details are provided to support the claim.

  7. Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models

    cs.CL 2025-06 reject novelty 3.0 of 10

    A survey of LLM hallucination research that formalizes hallucination types and argues, via incompleteness and undecidability arguments, that hallucinations cannot be fully eliminated.

  8. Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality

    cs.CL 2025-08 conditional novelty 2.0 of 10

    A thesis that combines self-learning from dialog logs, schema-guided prompting, and self-aligned factuality to build task bots with minimal human intervention.

Pith tools