- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work aims to provide a framework of formalism for scoring sequential text-model’s answers to questions, both in terms of semantic equivalence and score scale.
Critical strengths
- The idea of extending the scoring to free generation is interesting
- The figures and tables are very clear
Critical weaknesses
- The primary motivation provided for this work is to find an explanation for the well-recorded gap in accuracy when the LLM is used to generate an answer compared to when an answer is probed from the hidden state more directly. The conclusion of the work seems to be that if the list of clustered answer candidates is provided then there is no gap, which is somewhat in contradiction to the literature which mostly shows that probes trained on exactly such a representation (A_c) can improve performance.
- There are several incoherences in the flow of the methodology. Equation (6) is never really used or referred to afterwards. The measurement scale criterion is meaningless: as it is written, if I apply some arbitrary increasing function T to the log-scores then I achieve common scale. I can’t see why this is necessary if I already have an order preserving measurement (eq. 5). We never see a function notated T again in the main text. The authors chose to refer to the probability of an answer cluster P_q(A) as “answer support”, which is confusing since the “support” induced by a distribution P(X) typically means the set of values that X can take for which P(X) is defined. Equation 1, in particular the left expression for u_q = … is impossible to understand as the # notation is not defined. For this equation, an entire probability textbook is cited.
- Novelty is weak: both the notion of candidate-ordering and semantic clustering have already been established. A proof for the existence of a probe (Proposition 3.1) is not really necessary in my view.
- Impact: the claimed contributions are not particularly impactful:
- “we develop a measurement theory […]”: the proposed measurement theory does not provide any real new insight I
- “Through four native […]”: in plain language, the authors make this contribution by demonstrating that including both the set of answer choices and prompting to avoid answer equivalence issues improves performance, something that is both evident and well-known
- “We develop a shared-map construction […]”: in plain language, the authors implement a probe and show that it can improve on bad prompting strategies (although not enough to beat good prompting strategies).
Based on these weaknesses, I am rating the paper a clear rejection.
Questions for authors
- Figure 1: for T_s, do you count commitment flips between two semantically equivalent answers?