REVIEW 7 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.
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
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.
Forward citations
Cited by 7 Pith papers
-
Cross-Layer Attention Probing for Fine-Grained Hallucination Detection
CLAP, a cross-layer attention probe over all LLM layer activations, improves hallucination detection and enables a detect-then-mitigate decoding strategy.
-
SGIC: A Self-Guided Iterative Calibration Framework for RAG
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.
-
Maximally-Informative Retrieval for State Space Model Generation
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.
-
Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs
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.
-
From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered
LLM uncertainty quantification should be judged by whether it improves real human decisions, not by calibration scores on trivia benchmarks.
-
Confidence Estimation for Text-to-SQL in Large Language Models
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.
-
Toward Better Generalisation in Uncertainty Estimators: Leveraging Data-Agnostic Features
Adding data-agnostic probability and entropy features to hidden-state probes improves cross-task generalization in most but not all evaluated transfer pairs.
Discussion (0). Sign in to comment.