Explanation Generation

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

9 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 92 papers with code (235 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Using Stratified Sampling to Improve LIME Image Explanations
  26 Mar 2024 2 repositories listed
  We investigate the use of a stratified sampling approach for LIME Image, a popular model-agnostic explainable AI method for computer vision tasks, in order to reduce the artifacts generated by typical Monte Carlo…
• MACRec: a Multi-Agent Collaboration Framework for Recommendation
  23 Feb 2024 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks.
• Explaining black box text modules in natural language with language models
  17 May 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
• Explaining Patterns in Data with Language Models via Interpretable Autoprompting
  4 Oct 2022 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks.
• TE2Rules: Explaining Tree Ensembles using Rules
  29 Jun 2022 2 repositories listed
  Tree Ensemble (TE) models, such as Gradient Boosted Trees, often achieve optimal performance on tabular datasets, yet their lack of transparency poses challenges for comprehending their decision logic.
• AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations
  26 Aug 2021 2 repositories listed
  We propose AR-BERT, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models.
• Explainable Automated Fact-Checking for Public Health Claims
  19 Oct 2020 2 repositories listed
  We present the first study of explainable fact-checking for claims which require specific expertise.
• RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
  14 Jun 2025 1 repository listed
  Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation.
• LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference
  28 May 2025 1 repository listed
  There is increasing evidence of Human Label Variation (HLV) in Natural Language Inference (NLI), where annotators assign different labels to the same premise-hypothesis pair.
• Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation
  26 May 2025 1 repository listed
  This paper investigates how rationale quality impacts SLM performance in mental health detection and explanation generation.
• SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation
  19 May 2025 1 repository listed
  Adapting to the addressee is crucial for successful explanations, yet poses significant challenges for dialogsystems.
• Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
  26 Mar 2025 1 repository listed Syntology ran 3 of 11 samples · 8 unverified
  Deepfake detection is a long-established research topic vital for mitigating the spread of malicious misinformation.
• Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
  11 Feb 2025 1 repository listed
  TURBO assumes the target of the sarcasm and guides the multimodal shared fusion mechanism in learning intricacies of the intended irony for explanations.
• Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
  7 Feb 2025 1 repository listed
  To address this, we investigate how to use existing explanation datasets for self-rationalization and evaluate models' out-of-distribution (OOD) performance.
• IndMask: Inductive Explanation for Multivariate Time Series Black-Box Models
  20 Oct 2024 1 repository listed
  In this paper, we introduce IndMask, a framework for explaining decisions of black-box time series models.
• Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation
  5 Oct 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We propose a label-adaptive learning approach: first, we fine-tune a model to learn veracity prediction with annotated labels (step-1 model).
• Multimodal Coherent Explanation Generation of Robot Failures
  1 Oct 2024 1 repository listed
  The explainability of a robot's actions is crucial to its acceptance in social spaces.
• FMDLlama: Financial Misinformation Detection based on Large Language Models
  24 Sep 2024 1 repository listed
  The emergence of social media has made the spread of misinformation easier.
• Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
  22 Sep 2024 1 repository listed
  With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items.
• Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
  11 Sep 2024 1 repository listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  Additionally, we conduct an ablation study to assess the importance of feedback and suggestions.
• Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information
  18 Jul 2024 1 repository listed
  However, as current explanation generation methods are commonly trained with an objective to mimic existing user reviews, the generated explanations are often not aligned with the predicted ratings or some important…
• XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
  16 Jul 2024 1 repository listed Syntology ran 10 of 11 samples · 1 unverified · 11 pointer-only (licence)
  Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability through visual and textual explanations to end-users.
• Preference Distillation for Personalized Generative Recommendation
  6 Jul 2024 1 repository listed
  Recently, researchers have investigated the capabilities of Large Language Models (LLMs) for generative recommender systems.
• Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
  19 Jun 2024 1 repository listed
  RLHEX provides a flexible framework to incorporate different human-designed principles into the counterfactual explanation generation process, aligning these explanations with domain expertise.
• Evaluating Evidence Attribution in Generated Fact Checking Explanations
  18 Jun 2024 1 repository listed
  Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations.
• Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech
  6 Jun 2024 1 repository listed
  Employing language models to generate explanations for an incoming implicit hate post is an active area of research.
• Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models
  15 May 2024 1 repository listed
  This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or…
• Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
  29 Apr 2024 1 repository listed
  However, it is not clear to what extent they are using the input vision and text modalities when generating answers or explanations.
• RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict
  25 Mar 2024 1 repository listed
  Furthermore, we construct RU22Fact, a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples, each containing real-world claims, optimized evidence, and referenced…
• Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
  15 Mar 2024 1 repository listed Syntology ran 8 of 9 samples · 1 unverified · 9 pointer-only (licence)
  Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration.

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.