AI ethics evidence index Search
Source-linked daily record
Evidence record 12354 · automatically gathered

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality. In this work, we investigate how instruction-tuned Transformer models (LLaMA and Mistral) encode discourse relations in English, with a particular focus on the contrasting relations of causation and antithesis. Framing the task as a next-token prediction task and applying a suite of interpretability techniques to test model internals, our findings show that c

Record details

Published: 20 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 22 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Also mentions Mistral · Shared topic: Finance, VC & PE

Math Education Digital Shadows for Investigating Learning with GenAI: Mathematics Performance, Anxiety, and Confidence in LLMs

arXiv cs.CY · 27 July 2026

Also mentions Mistral · Shared topic: Finance, VC & PE

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

arXiv · 9 June 2026

Also mentions Mistral · Shared topic: Safety & alignment

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

arXiv · 1 June 2026

Also mentions Mistral · Shared topic: Safety & alignment

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science

arXiv · 12 May 2026

Also mentions Mistral · Shared topic: Safety & alignment

Phoenix-VL 1.5 Medium Technical Report

arXiv · 11 May 2026

Also mentions Mistral · Shared topic: Safety & alignment

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

arXiv · 1 May 2026

How to cite this record

ethics.ai (20 July 2026), “For What Reason? Interpreting Models' Encoding of Causation and Antithesis,” evidence record 12354, https://ethics.ai/record/12354 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.