Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Post-training for Efficient Communication via Convention Formation

Yilun Hua, Evan Wang, Yoav Artzi

Published

Aug 8, 2025

Citations

0

Trust level

Low

Usefulness score

40/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 28, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Demonstrations General

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

Background context only.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
40/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this behavior. We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation. We evaluate with two new benchmarks focused on this capability. First, we design a focused, cognitively-motivated interaction benchmark that consistently elicits strong convention formation trends in humans. Second, we create a new document-grounded reference completion task that reflects in-the-wild convention formation behavior. Our studies show significantly improved convention formation abilities in post-trained LLMs across the two evaluation methods.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

partial

Demonstrations

Directly usable for protocol triage.

"We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Demonstrations
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.
  • In contrast, prior work shows that LLMs do not naturally show this behavior.
  • We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.
  • We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation.
  • We evaluate with two new benchmarks focused on this capability.

Why it matters for eval

  • Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.
  • We evaluate with two new benchmarks focused on this capability.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.