SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.20600 · NeurIPS · 2024

Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol

Karan Bania, Harshvardhan Mestha, Vinaya Shreyas, Sathyanarayana, Sidong Liu, Ashwin Srinivasan

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.20600.json · badge: /api/ran/2410.20600.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
karannb/interact canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
encode_image Ran
ran; our contract draft was wrong, not the code
karannb/interact/src/utils.py
code served (permissive licence) · get_code("d193df7c20c2973f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import base64
import tempfile
import os

# Create a temporary image file for testing
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.png') as tmp_file:
    # Write minimal PNG data (1x1 transparent pixel)
    png_data = (
        b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01'
        b'\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01'
        b'\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82'
    )
    tmp_file.write(png_data)
    image_path = tmp_file.name

ARGS = {
    'image_path': image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
summarize Ran
ran; our contract draft was wrong, not the code
karannb/interact/src/utils.py
code served (permissive licence) · get_code("5939f41f939a5624")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import litellm

# Mock the litellm.completion function to avoid actual API calls
original_completion = litellm.completion

def mock_completion(**kwargs):
    """Mock completion that returns a structured response"""
    class MockMessage:
        def __init__(self):
            self.content = "The radiology report shows findings consistent with Pneumonia including consolidation in the right lower lobe. Recommend follow-up imaging in 4 weeks."
    
    class MockChoice:
        def __init__(self):
            self.message = MockMessage()
    
    class MockCompletion:
        def __init__(self):
            self.choices = [MockChoice()]
    
    return MockCompletion()

litellm.completion = mock_completion

# Define arguments for the summarize function
ARGS = {
    'report': 'Patient ID: 12345, Age: 65, Name: John Doe. Radiology Report: Portable chest radiograph obtained. There is consolidation in the right lower lobe consistent with pneumonia. The left lung appears clear. Heart size is normal. No pleural effusion. No pneumothorax. Impression: Right lower lobe pneumonia. Report by Dr. Smith. Link: https://example.com/report',
    'ailment': 'Pneumonia'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
litellm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
encode_image 76 other papers
31 dated earlier, 12 the same month, 32 later, 1 same year, order not determinable
2309.05950 (2023-09)
Language Models as Black-Box Optimizers for Vision-Language Models
2311.15732 (2023-11)
GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
2312.14867 (2023-12)
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
and 73 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Our interest is in the design of software systems involving a human-expert interacting-using natural language-with a large language model (LLM) on data analysis tasks. For complex problems, it is possible that LLMs can harness human expertise and creativity to find solutions that were otherwise elusive. On one level, this interaction takes place through multiple turns of prompts from the human and responses from the LLM. Here we investigate a more structured approach based on an abstract protocol described in [3] for interaction between agents. The protocol is motivated by a notion of "two-way intelligibility" and is modelled by a pair of communicating finite-state machines. We provide an implementation of the protocol, and provide empirical evidence of using the implementation to mediate interactions between an LLM and a human-agent in two areas of scientific interest (radiology and drug design). We conduct controlled experiments with a human proxy (a database), and uncontrolled experiments with human subjects. The results provide evidence in support of the protocol's capability of capturing one-and two-way intelligibility in human-LLM interaction; and for the utility of two-way intelligibility in the design of human-machine systems. Our code is available at https://github.com/karannb/interact.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.20600")
get_code_for_paper("2410.20600")
have("2410.20600")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.20600.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.20600.svg)](https://syntology.ai/paper/2410.20600)

Connect an agent — have() is free.