# Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently

arXiv: https://arxiv.org/abs/2401.06640 · HTML: https://mlsanity.com/paper/2401.06640/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 12 Jan 2024.

## Builds on (most cited first, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks](https://mlsanity.com/paper/2001.03632/) (2020)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations](https://mlsanity.com/paper/2305.13299/) (2023)
- [Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations](https://mlsanity.com/paper/2109.14989/) (2021)
- [The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative](https://mlsanity.com/paper/2210.13181/) (2022)
- [Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema](https://mlsanity.com/paper/2104.08161/) (2021)
- [Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models](https://mlsanity.com/paper/2203.09397/) (2022)
- [Sorting through the noise: Testing robustness of information processing in pre-trained language models](https://mlsanity.com/paper/2109.12393/) (2021)
- [When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it](https://mlsanity.com/paper/2205.03472/) (2022)
- [Language model acceptability judgements are not always robust to context](https://mlsanity.com/paper/2212.08979/) (2022)
- [In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax](https://mlsanity.com/paper/2311.07811/) (2023)
- [Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations](https://mlsanity.com/paper/1906.04068/) (2019)

## Built on by (most cited first, 3 of 3)

- [Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models](https://mlsanity.com/paper/2403.14859/) (2024)
- [Characterizing the Role of Similarity in the Property Inferences of Language Models](https://mlsanity.com/paper/2410.22590/) (2024)
- [Trick or Neat: Adversarial Ambiguity and Language Model Evaluation](https://mlsanity.com/paper/2506.01205/) (2025)

## Abstract (arXiv)

Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction. However, it is now well known that LMs can demonstrate radical improvements in the presence of experimental contexts such as in-context examples and instructions. How well does this translate to previously studied meaning-sensitive tasks? We present a case-study on the extent to which experimental contexts can improve LMs' robustness in performing property inheritance -- predicting semantic properties of novel concepts, a task that they have been previously shown to fail on. Upon carefully controlling the nature of the in-context examples and the instructions, our work reveals that they can indeed lead to non-trivial property inheritance behavior in LMs. However, this ability is inconsistent: with a minimal reformulation of the task, some LMs were found to pick up on shallow, non-semantic heuristics from their inputs, suggesting that the computational principles of semantic property inference are yet to be mastered by LMs.