- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper is trying to evaluate the uncertainty of language model even when the judge is weak to decide what meaning each answer belongs to. Under the setting of at most 4 meanings for answers, this work conducted the lower bound and upper bound of the semantic entropy for these answers by fully utilizing structures on judge graph.
Critical strengths
S1: The design and derivation of the lower bound and upper bound for semantic entropy is ingenious and rigorous. And this work pushes the bound from at most three meanings setting to at most four meanings setting, which can bring some insights to the community.
Critical weaknesses
W1: The work is really difficult to follow. The presentation of this paper does not provide enough background explanation to the motivation. It is hard to know why the authors need to find the minimax rate of semantic entropy for at most four meanings, which is not a practical setting in real life.
W2: The anonymous concurrent submission that give the proof under at most 3 meanings is not properly cited. And the reliability of such work is doubtful.
Questions for authors
Q1: Is it reasonable to use the same q and delta for all responses? Why do this?
Q2: Why assume that there are at most four meanings? Would such a restrictive assumption be still limiting even it has made contribution to existing work?
Q3: How can we know the distinguish ability of judger? It looks like is importance for the estimation, but knowing in real life is not very simple.
2 comments
Response to Reviewer 3YVX (2/2): W2 and Q1 to Q3
W2. The concurrent anonymous submission.
Citation. The citation is anonymous because that manuscript is under double-blind review. The bibliography entry carries no title, however, which makes it less informative than it should be. We will replace it with an anonymous entry that carries the title.
Reliability. All results used in our proofs are established within this submission. The tools that the two papers share are restated here with their proofs, and the concurrent manuscript is cited for comparison and context: its three-meaning rate and threshold, the statement that the meanings cannot be recovered once , and two results mentioned in Appendix A that we do not treat. None of these is a premise of a proof in this paper, so Theorems 1, 2 and 7 and Corollaries 3 and 8 can be checked without it. The first paragraph of Appendix A separates the shared ingredients, their extensions here, and the new arguments.
Q1. Is it reasonable to use the same and for all responses? Why do this?
It is a simplification, and it is exact in one situation beyond its literal reading. Suppose each pair has its own unobserved rates that give valid probabilities, are drawn independently across pairs and independently of all meanings, and have common means , and the verdicts are independent given the meanings and the rates. After the rates are integrated out, the verdict graph follows model (1) with the average rates, because the probability mass of a Bernoulli variable is affine in its parameter, and our theorems apply under their own hypotheses with . This is a statement about risk averaged over the rate draws, and it does not cover arbitrary fixed pair-specific rates. We will add it after the model.
Why this model: two rates are the smallest description of a judge that separates same-meaning pairs from different-meaning pairs, and they make the answer a formula in and . It is the standard model of a noisy pairwise oracle in the clustering literature (for example Mazumdar and Saha, 2017, with a symmetric error rate) and the observation model of the earlier analysis of semantic entropy by Liu (2026).
What the model does not cover: rates that depend on the meaning, and verdicts that are dependent because they share an answer; both are stated in the Limitations. In our experiments with real judges, the estimated rates vary between questions and between reference groups within a question; these differences include sampling noise, and the diagnostics do not separate rate heterogeneity from dependence.
Q2. Why at most four meanings? Is such an assumption still limiting?
W1 gives the reason for four. It is a limit of the paper, and Section 6 says so: prompts with more than four meanings are outside the theorems. In our experiments, the reference assigns at most four groups to the 30 answers of 56% to 61% of the evaluation questions, and most greedy answers that fail the gold-alias match lie in questions with more than four groups among their 30 answers; these are counts in a sample, not the support of the meaning distribution. For meanings we conjecture the threshold , which gives and for and decreases towards , so more meanings would require a stronger judge. Proving it needs a least-favourable path and an entropy transfer for general , which we do not have.
Q3. How can the distinguishing ability of the judge be known?
By measuring it on pairs whose relation is known. Take calibration verdicts on pairs of answers known to share a meaning and on pairs known to differ, independent of each other and of the estimation data. The two agreement frequencies and estimate and . Run Algorithm 1 with when , and return otherwise. Corollary 31(ii) bounds the resulting risk for every finite : provided , consistency is kept once , and for the rate of the upper bound is kept once . Corollary 31(i) gives the tolerance under its conditions: the rate survives an error in the two rates of order .
Some side information of this kind is needed: the concurrent analysis reports that with an unknown background rate the verdict graph alone does not permit uniform consistency in its weak regime. Labelled pairs are one sufficient source. The model describes one prompt, so reusing one calibration set across prompts requires that the same two rates apply to their answer populations, which is an additional assumption.
We hope these explanations make the motivation and the scope of the paper clearer, and we are glad to answer further questions before the discussion closes.
Response to Reviewer 3YVX (1/2): W1
Thank you for the review. We take the presentation score seriously. This reply first explains the motivation in plain terms, and we will rewrite the opening of the introduction along the same lines.
One clarification, since our presentation may have caused it: the upper and lower bounds in the paper are bounds on the error with which the entropy can be estimated, not bounds on the entropy itself. The upper bound limits the worst-case expected squared error of our estimator, and the lower bound is an error level that no estimator can beat on some meaning distribution.
W1. Presentation and motivation; why the minimax rate for at most four meanings.
In plain words. "Paris" and "the French capital" give one answer in different words. Semantic entropy measures how varied the meanings of a model's sampled answers are, and a judge decides which pairs of answers mean the same thing. The usual estimator groups the answers using these verdicts, so judge mistakes can distort its entropy estimate. We ask how accurately the entropy can be measured from such a judge, by any method.
The observation. With at most three meanings, the chances that two and that three independent answers share a meaning determine the entropy. Under model (1), these chances can be estimated by averaging adjusted verdicts over pairs of answers, and products of two adjusted verdicts that share one answer over triples, even when a single verdict is only slightly better than chance. Four meanings is the first case where two distributions can agree on both chances and still have different entropy. Averaging products of three adjusted verdicts from one answer to three others then estimates the missing fourth chance, that four answers share a meaning.
What the theorems say. The upper bound limits our estimator's worst-case expected squared error, and the lower bound shows that every estimator incurs an error of that order on some meaning distribution, in the stated regime. In symbols: write Δ for the judge's advantage, so that it says "equivalent" with probability q+Δ for a same-meaning pair and q otherwise. For q bounded away from 0 and 1, uniformly consistent estimation is possible if and only if n4Δ6→∞ (Corollary 3), and the best achievable worst-case squared error is of order min{1,(n4Δ6)−1/3} on the windows nΔ2≤n−κ (Theorems 1 and 2).
Why four. The distributions (21,41,41,0) and (0.45,0.4,0.1,0.05) both have P2=0.375 and P3=0.15625, the probabilities that two and that three answers share a meaning, yet their entropies differ by about 0.066 nats (Section 1). Four is also where the answer changes: for Δ=n−γ the critical exponent drops from 3/4 with three meanings, as reported in the concurrent work, to 2/3 with four, where uniformly consistent estimation requires γ<2/3. So the strength required of the judge depends on the number of meanings. "At most four" covers prompts with one, two, three or four meanings.
A real example, from the experiments we ran for this response (top-level comments "Experiments with real LLM samples and real judges"). Asked "With 47 attacks in the year 2010 alone, what body of water is known as Pirate Alley?", Llama-3.1-8B-Instruct gave 30 short answers that the reference grouped into four meaning groups: 18 say the Gulf of Mexico, 10 the Gulf of Aden (the correct answer), one the Gulf of Guinea and one the Cape of Campeche. The entropy of these proportions is 0.90 nats, and the model's greedy answer, "Gulf of Mexico", is wrong: the uncertainty that semantic entropy is meant to reveal. Among the 250 new short-answer questions, 19 have exactly four groups and 153 have at most four.
Besides the new opening of Section 1, we will add a notation table to the appendix and a worked example with concrete numbers of answers and judge calls to Section 2.