Pith. sign in

REVIEW 6 cited by

LM-Polygraph: Uncertainty Estimation for Language Models

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 2311.07383 v1 pith:CH5J7WTQ submitted 2023-11-13 cs.CL cs.LG

classification cs.CLcs.LG
keywords llmslm-polygraphmethodsmodelsdiscernestimationhoweverlanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e., fabricate facts without providing users an apparent means to discern the veracity of their statements. Uncertainty estimation (UE) methods are one path to safer, more responsible, and more effective use of LLMs. However, to date, research on UE methods for LLMs has been focused primarily on theoretical rather than engineering contributions. In this work, we tackle this issue by introducing LM-Polygraph, a framework with implementations of a battery of state-of-the-art UE methods for LLMs in text generation tasks, with unified program interfaces in Python. Additionally, it introduces an extendable benchmark for consistent evaluation of UE techniques by researchers, and a demo web application that enriches the standard chat dialog with confidence scores, empowering end-users to discern unreliable responses. LM-Polygraph is compatible with the most recent LLMs, including BLOOMz, LLaMA-2, ChatGPT, and GPT-4, and is designed to support future releases of similarly-styled LMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Hallucination detection in vision-language models is improved by classifying a structured pattern of consistency across image/text perturbations and statement/negation probes, rather than relying on one uncertainty score.

  2. Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

    cs.CL 2025-10 conditional novelty 6.0 of 10

    Explicitly instructing LLM agents to quit uncertain or risky tasks improves their safety scores by 0.39 on average in ToolEmu simulations, with a negligible average helpfulness decrease of 0.03.

  3. Unsupervised Hallucination Detection by Inspecting Reasoning Processes

    cs.CL 2025-09 conditional novelty 6.0 of 10

    IRIS detects LLM hallucinations by training a lightweight probe on hidden states elicited during the model's own step-by-step verification, using the model's verbalized confidence as soft pseudolabels.

  4. Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning

    cs.AI 2025-09 conditional novelty 6.0 of 10

    An LLM agent using retrieval and summary uncertainty as training rewards and inference filters produces more factual, useful multi-omics summaries and better downstream survival predictions.

  5. Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration

    cs.CV 2025-07 conditional novelty 5.0 of 10

    C-PEAL trains the active learning selector with a loss that raises entropy for wrong predictions and lowers it for correct ones, improving sample selection for CLIP-style models under prompt learning and LoRA.

  6. Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

    cs.CL 2025-05 reject novelty 5.0 of 10

    A grammar-based model of LLM-generated SMT-LIB code produces uncertainty signals that predict formalization errors on some reasoning tasks, with fused signals giving large error reductions only in an in-sample evaluation.

Pith tools