Pith. sign in

REVIEW 7 cited by

AlignScore: Evaluating Factual Consistency with a Unified Alignment Function

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 2305.16739 v1 pith:DDWL45PY submitted 2023-05-26 cs.CL

classification cs.CL
keywords alignscorealignmentfactualmetricsfunctioninformationtexttraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Many text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often depend on specific functions, such as natural language inference (NLI) or question answering (QA), trained on limited data. Those metrics thus can hardly assess diverse factual inconsistencies (e.g., contradictions, hallucinations) that occur in varying inputs/outputs (e.g., sentences, documents) from different tasks. In this paper, we propose AlignScore, a new holistic metric that applies to a variety of factual inconsistency scenarios as above. AlignScore is based on a general function of information alignment between two arbitrary text pieces. Crucially, we develop a unified training framework of the alignment function by integrating a large diversity of data sources, resulting in 4.7M training examples from 7 well-established tasks (NLI, QA, paraphrasing, fact verification, information retrieval, semantic similarity, and summarization). We conduct extensive experiments on large-scale benchmarks including 22 evaluation datasets, where 19 of the datasets were never seen in the alignment training. AlignScore achieves substantial improvement over a wide range of previous metrics. Moreover, AlignScore (355M parameters) matches or even outperforms metrics based on ChatGPT and GPT-4 that are orders of magnitude larger.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. 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.

  2. ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A residual-stream update metric, the ICR Score, and a lightweight probe built on it detect LLM hallucinations with higher AUROC than several baselines across three open models.

  3. BEnchmarking LLMs for Ophthalmology (BELO) for Ophthalmological Knowledge and Reasoning

    cs.CL 2025-07 conditional novelty 6.0 of 10

    BELO is a new ophthalmology benchmark of 900 expert-checked multiple-choice questions with reasoning, used to evaluate six LLMs on accuracy and explanation quality.

  4. Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations

    cs.AI 2025-06 conditional novelty 6.0 of 10

    SSP adds a learned, sample-specific noise prompt to an LLM input and scores hallucination by the cosine shift in intermediate representations, outperforming output-confidence baselines on QA benchmarks.

  5. Fact-Controlled Diagnosis of Hallucinations in Medical Text Summarization

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A fact-alignment LLM method detects clinical summarization hallucinations better than existing metrics, with correlations of 0.43 on controlled data and 0.37 on natural errors.

  6. CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A new 109-conversation, 86-API benchmark for LLM function-calling in multi-turn dialogue shows top models at about 40% accuracy and near-zero performance on chains of 4+ calls.

  7. UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Sentence selection, improved by self-consistency sampling with hand-tuned thresholds, is the main driver of answer quality in a small EHR question-answering shared task.

Pith tools