REVIEW 6 cited by
Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge
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
Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations, emphasizing the trade-off between honesty and helpfulness. To tackle the challenge of precisely determining LLMs' knowledge gaps, we diagnostically create unanswerable questions containing non-existent concepts or false premises, ensuring that they are outside the LLMs' vast training data. By compiling a benchmark, UnknownBench, which consists of both unanswerable and answerable questions, we quantitatively evaluate the LLMs' performance in maintaining honesty while being helpful. Using a model-agnostic unified confidence elicitation approach, we observe that most LLMs fail to consistently refuse or express uncertainty towards questions outside their parametric knowledge, although instruction fine-tuning and alignment techniques can provide marginal enhancements. Moreover, LLMs' uncertainty expression does not always stay consistent with the perceived confidence of their textual outputs.
Forward citations
Cited by 6 Pith papers
-
UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions
A new bilingual benchmark ties unanswerable questions to Wikidata facts and shows that LLMs often store the relevant knowledge yet fail to use it to recognize unanswerability.
-
Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs
A unified 16-category refusal taxonomy with human and synthetic datasets and a low-cost classifier for auditing refusal behavior in LLMs.
-
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
UAlign improves LLM factuality alignment by adding predicted confidence and semantic entropy as input features to prompts and the reward model, helping the model answer known questions and refuse unknown ones.
-
Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation
Test-time retrieval of committee-disagreement-mined synthetic images cuts a safety classifier's false-negative rate on a hard HoliSafe subset from 41.2% to 24.5%.
-
SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues
STREAM fine-tunes a small reasoning model on human-labeled, reason-annotated multi-turn dialogues and uses it to warn target LLMs, cutting average attack success rates by roughly half while keeping benchmark scores close.
-
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Adding a special refuse token to a fine-tuned LLM lets a developer tune refusal rates at inference time by thresholding the token's probability, with per-category control.
Discussion (0). Continue with ORCID to comment.