Papers with CALM
CALM-Bench: A Multi-task Benchmark for Evaluating Causality-Aware Language Models (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in foundation language models have shown the efficacy of pre-trained models across diverse QA tasks. |
| Approach: | They propose a multi-task benchmark for evaluating causality-aware language models to unify causal QA research. |
| Outcome: | The proposed model outperforms single-task fine-tuned models on the CALM-Bench tasks. |
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are pre-trained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. |
| Approach: | They propose to use the **C**ross-Lingual Self-**Aligning ability of **L**anguage **M**odels to align knowledge across languages. |
| Outcome: | The proposed model performs well in both zero-shot and retrieval-augmented settings. |
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. |
| Approach: | They propose a method to fine-tune language models in a goal-aware way . they evaluate a flight-booking method with a context-assisted language model . |
| Outcome: | The proposed method outperforms the state-of-the-art method on a flight-booking task by 7% in terms of task success. |
Open Information Extraction from Conjunctive Sentences (C18-1)
Copied to clipboard
| Challenge: | Recent work has highlighted the lack of proper conjunction processing as the most significant source of missed yield in Open IE. |
| Approach: | They develop a coordination analyzer that searches over hierarchical conjunct boundaries and uses a language model to score conjunctions. |
| Outcome: | The proposed system performs extraction over the simple sentences identified by CALM to obtain up to 1.8x yield with a moderate increase in precision compared to extractions from original sentences. |
Keep CALM and Explore: Language Models for Action Generation in Text-based Games (2020.emnlp-main)
Copied to clipboard
| Challenge: | Text-based games present a unique challenge for autonomous agents to operate in natural language and handle enormous action spaces. |
| Approach: | They propose a Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state. |
| Outcome: | The proposed model achieves a 69% improvement in average game score on unsupervised games . the proposed model is competitive with or better than other models that have access to ground truth admissible actions on half of the games tested . |
From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) often output text at a native level of speech, making them difficult to use for contexts where end-users are not fully proficient. |
| Approach: | They propose a framework to control the difficulty level of text generated by Large Language Models for contexts where end-users are not fully proficient. |
| Outcome: | The proposed framework surpasses GPT-4 and other models at fraction of the cost. |