Challenge: Large language models (LLMs) are prone to various forms of safety risks, such as learning and propagating societal biases and even creating harmful or deceptive content through jailbreak attacks.
Approach: They propose a framework for causally tracing multiple components simultaneously that systematically identifies the subsets of components most critical to a desired performance metric.
Outcome: The proposed method outperforms existing methods in identifying components critical to a desired performance metric.

Similar Papers

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach: They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome: The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.
Causal-LLM: A Unified One-Shot Framework for Prompt- and Data-Driven Causal Graph Discovery (2025.findings-emnlp)

Copied to clipboard

Challenge: Current causal discovery methods rely on pairwise or iterative strategies that fail to capture global dependencies, amplify local biases, and reduce overall accuracy.
Approach: They propose a framework for one-step full causal graph discovery using prompt-based discovery and a data-driven method for settings without metadata.
Outcome: The proposed framework outperforms state-of-the-art models by approximately 40% in edge accuracy on datasets like Asia and Sachs while maintaining strong performance on more complex graphs.
Causal Inference with Large Language Model: A Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Existing causal inference frameworks do not match human judgment in several key areas, such as domain knowledge, logical inference, and cultural context.
Approach: They propose to apply large language models to causal inference tasks . they summarize the main causal problems and approaches and compare their results .
Outcome: The proposed methods are compared with traditional methods in healthcare, finance, and economics.
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks evaluate contextual causal reasoning in fragmented settings, failing to ensure context consistency or cover the full causal hierarchy.
Approach: They use a unified context to benchmark large language models' contextual causal reasoning skills.
Outcome: The proposed benchmarks show that LLMs are susceptible to distraction by irrelevant but factually correct information at lower level of causality.
DoubleLingo: Causal Estimation with Large Language Models (2024.naacl-short)

Copied to clipboard

Challenge: Existing methods for causal estimation are inadequate for noisy text data.
Approach: They propose to use LLM-based nuisance models to estimate causal effects from non-randomized data using assumptions about the underlying data distribution.
Outcome: The proposed method reduces the relative absolute error by 10.4% over existing methods on the best available dataset.
CodeSCM: Causal Analysis for Multi-Modal Code Generation (2025.naacl-long)

Copied to clipboard

Challenge: Prior work has shown that multimodal prompts can be highly sensitive, where small adjustments might result in drastically different responses from the model.
Approach: They propose a Structural Causal Model (SCM) for analyzing multi-modal code generation using large language models (LLMs).
Outcome: The proposed model is based on the principles of Causal Mediation Analysis and quantifies the causal effects of different prompt modalities on the model.
Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links Across Modalities (2025.findings-acl)

Copied to clipboard

Challenge: Existing MLLMs lack robustness in multimodal causal reasoning compared to their performance in textual settings.
Approach: They propose a novel multimodal chain-of-thought (CoT) reasoning benchmark that leverages siamese images and text pairs to challenge MLLMs.
Outcome: The proposed benchmark leverages siamese images and text pairs to challenge MLLMs.
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing fine-tuning paradigms focus on aligning LLMs with task-specific objectives.
Approach: They propose a pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training.
Outcome: The proposed pipeline achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks.
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models have facilitated the development of Multimodal LLMs.
Approach: They propose a causal framework to interpret unimodal biases in visual question answering problems and a framework to integrate information from different modalities and mitigate biase.
Outcome: The proposed framework analyzes visual question answering (VQA) problems to assess their impact on predictions.
CausalGraph2LLM: Evaluating LLMs for Causal Queries (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have opened up new avenues for their use beyond standard Natural Language Processing tasks.
Approach: They propose a benchmark to evaluate the capabilities of Large Language Models (LLMs) they use over 700k queries to compare their encoding capabilities.
Outcome: The proposed benchmark compared LLMs on graph-level and node-level queries and open-sourced and closed models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations