SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.08802 · ICML · 2022

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

Hamed Firooz, Xiang Ren, Maziar Sanjabi, Aaron Chan, Lambert Mathias, Liang Tan, Shaoliang Nie, Xiaochang Peng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2112.08802.json · badge: /api/ran/2112.08802.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
facebookresearch/UNIREX canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
facebookresearch/unirex canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
_instances_aopc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/unirex/src/utils/eraser/metrics.py
pointer only (licence: NONE) · get_code("0812eabdc927a1ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/unirex when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

align_rationale_with_tokens Ran
ran; our contract draft was wrong, not the code
facebookresearch/UNIREX/scripts/build_dataset.py
pointer only (licence: NONE) · get_code("0a8da4fad887581e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/UNIREX when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_aopc_scores Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/unirex/src/utils/eraser/metrics.py
pointer only (licence: NONE) · get_code("8d306219cb0e2491")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/unirex when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

stratified_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/UNIREX/scripts/build_dataset.py
pointer only (licence: NONE) · get_code("a6a5ebcd8393d29c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/UNIREX when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

update_dataset_dict Ran
ran; our contract draft was wrong, not the code
facebookresearch/UNIREX/scripts/build_dataset.py
pointer only (licence: NONE) · get_code("3b27b863577b7303")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/UNIREX when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
align_rationale_with_tokens 1 other paper
1 later
2205.12542 (2022-05)
ER-Test: Evaluating Explanation Regularization Methods for Language Models
update_dataset_dict 1 other paper
1 later
2205.12542 (2022-05)
ER-Test: Evaluating Explanation Regularization Methods for Language Models

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

An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual behavior) and plausible (convincing to humans), without compromising the LM's (i.e., task model's) task performance. Although attribution algorithms and select-predict pipelines are commonly used in rationale extraction, they both rely on certain heuristics that hinder them from satisfying all three desiderata. In light of this, we propose UNIREX, a flexible learning framework that generalizes rationale extractor optimization as follows: (1) specify architecture for a learned rationale extractor; (2) select explainability objectives (i.e., faithfulness and plausibility criteria); and (3) jointly train the task model and rationale extractor on the task using the selected objectives. UNIREX enables replacing prior works' heuristic design choices with a generic learned rationale extractor in (1) and optimizing it for all three desiderata in (2)-(3). To facilitate comparison between methods with respect to multiple desiderata, we introduce the Normalized Relative Gain (NRG) metric. On five English text classification datasets, our best UNIREX configuration outperforms baselines by an average of 32.9% NRG. Plus, UNIREX rationale extractors' faithfulness can even generalize to unseen datasets and tasks. †

For agents

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

get_harvested_code_for_paper("2112.08802")
get_code_for_paper("2112.08802")
have("2112.08802")

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

curl https://syntology.ai/api/ran/2112.08802.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.08802.svg)](https://syntology.ai/paper/2112.08802)

Connect an agent — have() is free.