Papers with causal mechanisms
Grounding Gradable Adjectives through Crowdsourcing (L18-1)
Copied to clipboard
| Challenge: | Often, texts describe interactions using vague, high-level language . crowdsourcing is expensive and requires extensive literature review and time . |
| Approach: | They propose a method for estimating concrete groundings for a set of gradable adjectives by crowdsourcing human intuitions and fitting a mixed effects model to the text. |
| Outcome: | The proposed model can generalize to unseen data and has a predictive R 2 of 0.632 in general and 0.677 on a subset of high-frequency adjectives. |
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis (2024.findings-emnlp)
Copied to clipboard
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez Adauto, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan
| Challenge: | Sentiment analysis aims to identify the sentiment expressed in a piece of text, often in the form of a review. |
| Approach: | They propose a causal discovery task that distinguishes whether a review "primes" the sentiment and a traditional prediction task to model the sentiment using the review as input. |
| Outcome: | The proposed model improves by 32.13 F1 points on a zero-shot five-class SA. |
NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Lexical semantic change has been investigated with observational and experimental methods, but observational methods cannot get at causal mechanisms. |
| Approach: | They introduce a neural-agent framework designed to simulate semantic change by first grounding agents in a real lexical system and then manipulating their communicative needs. |
| Outcome: | The proposed framework simulates the evolution of a lexical system within a single generation by grounding agents in a real lexicon and manipulating their communicative needs. |
Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM-based methods rely on implicit language-level reasoning, resulting in opaque causal assumptions and fragile predictions. |
| Approach: | They propose an explicit and auditable causal reasoning framework for context-free intervention-based question answering that uses four modular stages rather than implicit end-to-end prediction. |
| Outcome: | The proposed framework outperforms existing LLM-based methods while providing interpretable and auditable causal reasoning traces. |
Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Emotional Support Conversation (ESC) are mechanistically opaque and lacks a causal mechanism between dialogue features and effective empathic strategies. |
| Approach: | They propose a framework that uses Doubly Robust learning to model causal effects of utterance features on strategy selection. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines in empathy and helpfulness and provides a theoretically grounded, interpretable solution to the mechanistic interpretability dilemma in affective computing. |
Uncovering Sentiment Analysis Circuit in Large Language Model (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that sentiment is encoded linearly in LLM representations, but their ability to utilize this information remains fragile to prompt variations. |
| Approach: | They propose a simple inference-time intervention method that amplifies circuit features to compensate for insufficient activation. |
| Outcome: | The proposed method improves on a sentiment analysis circuit with sparse autoencoders and circuit-level analysis. |
Revisiting the Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems (2024.lrec-main)
Copied to clipboard
| Challenge: | This study highlights the pervasive existence of gender stereotypes in literary works and proposes a model with 97% accuracy to identify gender bias. |
| Approach: | They propose a large language model with 97% accuracy to identify gender bias in rhymes and poems and a model with a comparative survey against human educator rectifications. |
| Outcome: | The proposed model has 97% accuracy and can be used to identify gender biases in rhymes and poems. |
CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing classification-based methods capture noise and spurious correlations while overlooking the underlying causal mechanisms. |
| Approach: | They propose a hallucination detection framework based on structural causal models that captures static and passive signals from internal states and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise. |
| Outcome: | Experiments on four datasets and three widely used LLMs show that the proposed framework improves AUROC and interpretability. |