Papers by Nicholas Asher
SSA: Improving Performance With a Better Scoring Function (2026.acl-long)
Copied to clipboard
| Challenge: | Despite the success of in-context learning, recent studies have identified systematic limitations in its generalization behavior. |
| Approach: | They propose a new attention scoring function that mitigates failures in transformer models . they use Scaled Signed Averaging to train the scoring function instead of Softmax . |
| Outcome: | The proposed scoring function outperforms transformer models with Softmax on NLP benchmarks and linguistic probing tasks. |
In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit surprising abilities across a variety of language tasks. |
| Approach: | They propose an algorithm which selects a coreset by analyzing correlation between training and evaluation samples with a trained model. |
| Outcome: | The proposed algorithm can achieve similar performance with just 50% of the training data while preserving the accuracy of the existing model. |
Weak Supervision for Learning Discourse Structure (D19-1)
Copied to clipboard
| Challenge: | a weak supervision approach is a promising tool for learning discourse structure for multi-party dialogue. |
| Approach: | They propose a data programming paradigm that allows a user to label training data using expert-composed heuristics and transform them into probability distributions of the class labels. |
| Outcome: | The proposed approach outperforms both deep learning and traditional ML approaches on the task of learning discourse structure for multi-party dialogue. |
Limits for learning with language models (2023.starsem-1)
Copied to clipboard
| Challenge: | Recent studies show that large language models fail to capture important aspects of linguistic meaning . authors argue that LLMs cannot learn fundamental semantic properties defined in formal semantics . |
| Approach: | They propose a theoretical explanation for some of the observed failings of large language models . they show that LLMs cannot learn certain fundamental semantic properties . |
| Outcome: | The proposed model fails to learn semantic entailment and consistency as defined in formal semantics, the authors argue . their model fails on tasks that require engorgements and deep linguistic understanding, they argue - but not on universal quantification. |
Learning Semantic Structure through First-Order-Logic Translation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that transformer-based language models can confuse which predicates apply to which objects . a this is a crucial building block of semantic structure, but if an LM mixes up which objects have which property, it makes errors in reasoning . |
| Approach: | They propose to use transformer-based language models to learn predicate argument structure from simple sentences. |
| Outcome: | The proposed model can learn predicate argument structure from simple sentences. |
Discourse Structure for the Minecraft Corpus (2024.lrec-main)
Copied to clipboard
| Challenge: | a discourse annotated version of the Minecraft Dialogue Corpus is a new linguistic resource for human-computer interaction . a recent study shows that inferring excecutable actions from language is difficult in the Minecraft setting . |
| Approach: | They propose a discourse annotated version of the Minecraft Dialogue Corpus . they train a parser with a novel "2 pass architecture" that gives excellent results . |
| Outcome: | The proposed model performs well on attachment prediction and relation labeling tasks especially long distance attachments. |
Data Programming for Learning Discourse Structure (P19-1)
Copied to clipboard
| Challenge: | Discourse structures are a relational semantic structure that convey causal, topical, argumentative relations or more generally coherence relations. |
| Approach: | They propose to use Snorkel to label training data using expert-composed heuristics and transform them into probability distributions of the class labels given to training candidates. |
| Outcome: | The proposed paradigm can be used for difficult tasks such as that of discourse attachment. |
EIFFEL: a novel benchmark to measure bias of English heavy training on French idiomatic expressions (2026.acl-long)
Copied to clipboard
| Challenge: | Mainstream multilingual models are generally trained on a much higher proportion of English data . this raises questions about their ability to capture linguistic features specific to non-English languages . |
| Approach: | They propose a benchmark to test multilingual LLMs' ability to capture linguistic features in other languages. |
| Outcome: | The proposed benchmark shows that multilingual models can capture features in non-English languages and cultural norms. |
Nebula: A discourse aware Minecraft Builder (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work has shown that at least some context is needed to understand and carry out conversationally given instructions. |
| Approach: | They propose to incorporate prior discourse and nonlinguistic contexts of a conversation situated in a nonlinguistic environment into an LLM model to improve the "language to action" component of collaborative tasks. |
| Outcome: | The proposed model doubles the baseline on the task of Jayannavar et al. (2020) and can construct shapes and understand location descriptions using a synthetic dataset. |
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent debates have shown that attention maps and attribution methods are unreliable. |
| Approach: | They propose a model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization to discover concepts the model leverages to make predictions. |
| Outcome: | The proposed technique generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task without compromising the accuracy of the underlying model or requiring a new one to be trained. |
Interpreto: An Explainability Library for Transformers (2026.acl-demo)
Copied to clipboard
Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, Francois Hoofd, Raphael Bernas, Nicholas Asher, Celine Hudelot, Fanny Jourdan
| Challenge: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . documentation or metrics are sometimes missing due to the complexity of the pipeline . |
| Approach: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . authors welcome issues and pull requests . |
| Outcome: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . the library welcomes issues and pull requests . |
Strong hallucinations from negation and how to fix them (2024.findings-acl)
Copied to clipboard
| Challenge: | Despite great performance on many tasks, language models still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. |
| Approach: | They propose a way to treat negation as an operation over latent representations that constrains how they may evolve. |
| Outcome: | The proposed approach improves model performance in cloze prompting and natural language inference tasks without training on sparse negative data. |
Llamipa: An Incremental Discourse Parser (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Discourse parsing is a task of predicting relationships between utterances and their semantic content . lack of surface cues in discourse graphs forces parsers to rely on deep, semantic information . a large language model (LLM) can significantly improve discourse parser performance . |
| Approach: | They propose a large language model (LLM) that leverages discourse context to parse a discourse . this model provides local, context-sensitive representations of discourse units . |
| Outcome: | The proposed model can provide local, context-sensitive representations of discourse units . it can process discourse data incrementally, which is essential for later use of discourse information . |
A simple but effective model for attachment in discourse parsing with multi-task learning for relation labeling (2023.eacl-main)
Copied to clipboard
| Challenge: | a discourse parsing model for conversation trained on the STAC is hard due to the complexity of discourse graphs and the frequent lack of surface cues provided by EDUs. |
| Approach: | They propose a discourse parsing model for conversation trained on the STAC that encodes discourse units and uses a multitask setting to predict relation labels. |
| Outcome: | The proposed model outperforms state-of-the-art models for discourse attachment prediction with no loss in performance for attachment. |
TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models typically come with a fixed architecture, but not all layers contribute equally to every downstream task. |
| Approach: | They propose an inference-time method that selectively removes irrelevant or detrimental layers . the method is hardware-agnostic, requires no retraining, and operates entirely at inference time . |
| Outcome: | The proposed method matches or surpasses baseline performance while reducing computational costs. |