Pith. sign in

REVIEW 12 cited by

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2307.01379 v3 pith:NKHZS4MK submitted 2023-07-03 cs.CL cs.AIcs.LG

Jinhao Duan , Hao Cheng , Shiqi Wang , Alex Zavalny , Chenan Wang , Renjing Xu , Bhavya Kailkhura , Kaidi Xu This is my paper
classification cs.CLcs.AIcs.LG
keywords languagellmsuncertaintyattentionequallyfree-formlargemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) show promising results in language generation and instruction following but frequently "hallucinate", making their outputs less reliable. Despite Uncertainty Quantification's (UQ) potential solutions, implementing it accurately within LLMs is challenging. Our research introduces a simple heuristic: not all tokens in auto-regressive LLM text equally represent the underlying meaning, as "linguistic redundancy" often allows a few keywords to convey the essence of long sentences. However, current methods underestimate this inequality when assessing uncertainty, causing tokens with limited semantics to be equally or excessively weighted in UQ. To correct this, we propose Shifting Attention to more Relevant (SAR) components at both token- and sentence-levels for better UQ. We conduct extensive experiments involving a range of popular "off-the-shelf" LLMs, such as Vicuna, WizardLM, and LLaMA-2-chat, with model sizes extending up to 33B parameters. We evaluate various free-form question-answering tasks, encompassing domains such as reading comprehension, science Q&A, and medical Q&A. Our experimental results, coupled with a comprehensive demographic analysis, demonstrate the superior performance of SAR. The code is available at https://github.com/jinhaoduan/SAR.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

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

  1. Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

    cs.CL 2025-05 conditional novelty 7.0 of 10

    EverGreenQA and EG-E5 provide a multilingual, human-labeled evergreen question classifier that improves self-knowledge estimation and QA dataset curation.

  2. Cross-Layer Attention Probing for Fine-Grained Hallucination Detection

    cs.CL 2025-09 conditional novelty 6.0 of 10

    CLAP, a cross-layer attention probe over all LLM layer activations, improves hallucination detection and enables a detect-then-mitigate decoding strategy.

  3. SGIC: A Self-Guided Iterative Calibration Framework for RAG

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SGIC feeds a model's own uncertainty scores back into its prompt for several calibration rounds and improves RAG accuracy on HotpotQA, NQ, and GSM8K.

  4. Maximally-Informative Retrieval for State Space Model Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RICO ranks documents by how much they reduce an SSM's question perplexity, using gradient-document inner products, and matches BM25 while often beating E5 on answer quality without finetuning.

  5. Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity

    cs.LG 2025-05 conditional novelty 6.0 of 10

    SNNE estimates LLM uncertainty from pairwise semantic similarities of sampled answers using a log-sum-exp aggregation, and it generalizes semantic entropy as a special case.

  6. Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Cleanse detects hallucinated LLM answers by computing the share of hidden-embedding cosine similarity that falls inside semantic clusters, and it beats several baselines in AUROC across four models and two QA benchmarks.

  7. From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered

    cs.CL 2025-06 conditional novelty 5.0 of 10

    LLM uncertainty quantification should be judged by whether it improves real human decisions, not by calibration scores on trivia benchmarks.

  8. Confidence Estimation for Text-to-SQL in Large Language Models

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    Consistency-based methods are the most reliable confidence signal for text-to-SQL in black-box LLMs, and executing queries against a database adds a useful correctness signal.

  9. Toward Better Generalisation in Uncertainty Estimators: Leveraging Data-Agnostic Features

    cs.AI 2025-07 conditional novelty 4.0 of 10

    Adding data-agnostic probability and entropy features to hidden-state probes improves cross-task generalization in most but not all evaluated transfer pairs.

  10. ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation

    cs.AI 2025-06 reject novelty 4.0 of 10

    ChemAU adds a position penalty to token-level uncertainty estimates so that flagged reasoning steps are corrected by a fine-tuned chemistry model, reporting improved accuracy on GPQA, MMLU-Pro, and SuperGPQA chemistry...

  11. HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Modeling the full token-by-token trajectory of LLM hidden states with neural ODEs, CDEs, and SDEs improves hallucination detection by over 14% AUC on a constructed true/false benchmark, though gains shrink on QA datasets.

  12. Towards Harmonized Uncertainty Estimation for Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    CUE combines a supervised correctness classifier with existing LLM uncertainty scores to improve indication, balance, and calibration, reporting AUROC and ECE gains across models and datasets.

Pith tools