FlowingFlowing
← Back to all development cases
Development case · blind model judgment pending independent human review; not a formal Benchmark conclusion.
AutocompleteJudgment incomplete32 / 162 · b1af3486a495101f

From Words to Molecules: A Survey of Large Language Models in Chemistry

Quantitative biology · 2402.01439v1

FLOWING EVIDENCE BENCHMARK

How do we tell whether Evidence helps?

At the same writing position, with the same model and task, how does supplying retrieved paper passages change the first output? We compare matched versions and retain ties, unusable outputs and incomplete reviews.

SAME DRAFT · EVIDENCE ON OR OFF

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED INPUTS

SHARED BY BOTH

Manuscript context, model, task and prompt

A · With Evidence

Retrieved paper passages supplied

B · Without Evidence

No retrieved passages supplied

LLM

Same model and version

A → first output

B → first output

Blind judge agent

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Order check: X / Y → Y / X

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The judge sees the same draft and both first outputs without knowing which received Evidence.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are autocomplete positions stratified?

Before seeing generation outcomes, we check whether a retrieved passage contains a specific proposition that directly supports the next writing move. Those positions appear in the left opportunity group; the rest are ordinary positions on the right. We select a balanced sample from admitted papers in each field. The 50/50 split is experimental, not a measure of how often either type occurs in writing.

AUTOCOMPLETE · 110

Biology, statistics and astrophysics

55 positions on each side; statistics uses the ten-paper rerun.

AUTOCOMPLETE · 52

Psychology and climate science

26 positions on each side; psychology includes nine papers and climate science four.

How are the table percentages calculated?

Across five fields, 51 of 81 left-column positions preferred the Evidence version. Ties, pairs where both versions were unusable and incomplete reviews remain in the denominator.

51Evidence version preferred
÷
81All positions in this group
=
63%Evidence preference in this group

Source contribution is a separate review: 16 of 22 Evidence wins entered into source review directly used retrieved papers; another 29 wins await review.

These are development-stage model judgments pending independent human review. They are not formal Benchmark conclusions and do not, on their own, establish causality.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

From Words to Molecules: A Survey of Large Language Models in Chemistry

6 Conclusion & Future Directions

To sum up, this survey offers a thorough exploration of the existing strategies for integrating LLMs into chemistry, covering the spectrum from input representation, through pretraining objectives, to diverse and unique applications. However, despite their rapid evolution, they remain in the nascent stages of development, indicating substantial room for growth and enhancement. The following future directions are pivotal for advancing the field:

…er et al. 2016 , with its 50,000 entries, barely scratches the surface of the vast and complex world of chemical retrosynthesis. This limitation significantly hampers the models’ ability to comprehend and predict chemical retrosynthesis accurately. Additionally, as chemistry evolves with quantum mechanics into quantum chemistry, chemical LLMs are still rooted in conventional theories. This gap underscores the pressing need for these models to integrate more deeply with advanced chemical knowledge, particularly from quantum chemistry, to stay relevant and effective in modern chemical research.

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionJudgment: Judgment incomplete

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Evidence

Same model and position · retrieved passages supplied · first output

Bridging this gap will require not only larger chemical corpora but also representations that encode quantum-mechanical quantities such as ground-state energies, which quantum computers have been proposed to compute.

Passages supplied to the Evidence version

Quantum Chemistry in the Age of Quantum Computing

Aspuru-Guzik et al. [45] first realized that quantum computers can be used for determining ground-state energies. This work lays the grounds for further research in quantum simulations for quantum chemistry, discussing choices of chemical basis, Hamiltonian mapping, simulation, and energy estimation…

Read full passage excerpt

Aspuru-Guzik et al. [45] first realized that quantum computers can be used for determining ground-state energies. This work lays the grounds for further research in quantum simulations for quantum chemistry, discussing choices of chemical basis, Hamiltonian mapping, simulation, and energy estimation.

No Evidence

Same model and position · no retrieved passages · first output

Beyond data scale and theoretical grounding, the field also lacks shared benchmarks that would allow chemical LLMs to be compared on equal footing. Establishing standardized evaluation suites for tasks such as retrosynthesis planning and molecular property prediction would make progress in this area measurable and cumulative.

Blind model judgment

The judgment was incomplete, so this case has no winner but remains in the denominator above.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.