ACL

Author: swabhs

_bibliography/papers.bib

@@ -23,6 +23,17 @@ @misc{finlayson2024logits
       abstract={The commercialization of large language models (LLMs) has led to the common practice of high-level API-only access to proprietary models. In this work, we show that even with a conservative assumption about the model architecture, it is possible to learn a surprisingly large amount of non-public information about an API-protected LLM from a relatively small number of API queries (e.g., costing under $1,000 for OpenAI's gpt-3.5-turbo). Our findings are centered on one key observation: most modern LLMs suffer from a softmax bottleneck, which restricts the model outputs to a linear subspace of the full output space. We show that this lends itself to a model image or a model signature which unlocks several capabilities with affordable cost: efficiently discovering the LLM's hidden size, obtaining full-vocabulary outputs, detecting and disambiguating different model updates, identifying the source LLM given a single full LLM output, and even estimating the output layer parameters. Our empirical investigations show the effectiveness of our methods, which allow us to estimate the embedding size of OpenAI's gpt-3.5-turbo to be about 4,096. Lastly, we discuss ways that LLM providers can guard against these attacks, as well as how these capabilities can be viewed as a feature (rather than a bug) by allowing for greater transparency and accountability.},
 }
 
+@misc{cui2024annotating,
+      title={Annotating FrameNet via Structure-Conditioned Language Generation},
+      author={Xinyue Cui and Swabha Swayamdipta},
+      url={../assets/pdf/papers/fn_conditioned_generation.pdf},
+      abbr={ACL},
+      year={2024},
+      selected=true,
+      preview={fn-conditioned-generation.jpeg},
+      abstract={Despite the mounting evidence for generative  capabilities of language models in understanding and generating natural language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate the task of generating new sentences preserving a given semantic structure, following the FrameNet formalism. We propose a framework to produce novel frame-semantically annotated sentences following an overgenerate-and-filter approach. Our results show that conditioning on rich, explicit semantic information tends to produce generations with high human acceptance, under both prompting and finetuning. Nevertheless, we discover that generated frame-semantic structured data is ineffective at training data augmentation for frame-semantic role labeling. Our study concludes that while generating high-quality, semantically rich data might be within reach, their downstream utility remains to be seen, highlighting the outstanding challenges with automating linguistic annotation tasks.},
+}
+
 @misc{nazari2024generative,
       title={Generative Explanations for Program Synthesizers},
       author={Amirmohammad Nazari and Souti Chattopadhyay and Swabha Swayamdipta and Mukund Raghothaman},

_bibliography/papers_orcid.bib

@@ -8,15 +8,7 @@ @misc{finlayson2024logits
       url={https://arxiv.org/abs/2403.09539},
 }
 
-@misc{cui2024annotating,
-      title={Annotating FrameNet via Structure-Conditioned Language Generation},
-      author={Xinyue Cui and Swabha Swayamdipta},
-      url={../assets/pdf/papers/fn_conditioned_generation.pdf},
-      abbr={Preprint},
-      year={2024},
-      preview={fn-conditioned-generation.jpeg},
-      abstract={Despite the mounting evidence for generative  capabilities of language models in understanding and generating natural language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate the task of generating new sentences preserving a given semantic structure, following the FrameNet formalism. We propose a framework to produce novel frame-semantically annotated sentences following an overgenerate-and-filter approach. Our results show that conditioning on rich, explicit semantic information tends to produce generations with high human acceptance, under both prompting and finetuning. Nevertheless, we discover that generated frame-semantic structured data is ineffective at training data augmentation for frame-semantic role labeling. Our study concludes that while generating high-quality, semantically rich data might be within reach, their downstream utility remains to be seen, highlighting the outstanding challenges with automating linguistic annotation tasks.},
-}
+
 
 @misc{nazari2024generative,
       title={Generative Explanations for Program Synthesizers},