Search Results for author:
Found 35 papers, 23 papers with code
QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding.
Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training
The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method.
2 OLMo 2 Furious
Our modified model architecture and training recipe achieve both better training stability and improved per-token efficiency.
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones.
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
We analyze features from the routing model to identify characteristics of instances that can benefit from human feedback, e. g., prompts with a moderate safety concern or moderate intent complexity.
SafetyAnalyst: Interpretable, transparent, and steerable LLM safety moderation
The ideal LLM content moderation system would be both structurally interpretable (so its decisions can be explained to users) and steerable (to reflect a community's values or align to safety standards).
Diverging Preferences: When do Annotators Disagree and do Models Know?
We find that the majority of disagreements are in opposition with standard reward modeling approaches, which are designed with the assumption that annotator disagreement is noise.
Explicating the Implicit: Argument Detection Beyond Sentence Boundaries
Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task.
Self-Directed Synthetic Dialogues and Revisions Technical Report
Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems.
The Art of Saying No: Contextual Noncompliance in Language Models
Chat-based language models are designed to be helpful, yet they should not comply with every user request.
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
High-quality preference data leads to improvements of up to 8% in instruction following and truthfulness.
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo.
Superlatives in Context: Modeling the Implicit Semantics of Superlatives
Semantically, superlatives perform a set comparison: something (or some things) has the min/max property out of a set.
RewardBench: Evaluating Reward Models for Language Modeling
To enhance scientific understanding of reward models, we present RewardBench, a benchmark dataset and code-base for evaluation.
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
Motivated by this discrepancy, we challenge the prevailing constrained evaluation paradigm for values and opinions in LLMs and explore more realistic unconstrained evaluations.
OLMo: Accelerating the Science of Language Models
Given the importance of these details in scientifically studying these models, including their biases and potential risks, we believe it is essential for the research community to have access to powerful, truly open LMs.
Promptly Predicting Structures: The Return of Inference
Can the promise of the prompt-based paradigm be extended to such structured outputs?
Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
Since the release of T\"ULU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques.
"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation
We compare models' analysis of this semantic structure across two settings: 1) direct production of AMR parses based on zero- and few-shot prompts, and 2) indirect partial reconstruction of AMR via metalinguistic natural language queries (e. g., "Identify the primary event of this sentence, and the predicate corresponding to that event.").
What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
From this model we distill a high-quality dataset, \delta-Rules-of-Thumb, of 1. 2M entries of contextualizations and rationales for 115K defeasible moral actions rated highly by human annotators 85. 9% to 99. 8% of the time.
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence.
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
To improve AI systems to better reflect value pluralism, the first-order challenge is to explore the extent to which AI systems can model pluralistic human values, rights, and duties as well as their interaction.
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities.
Revisiting Sentence Union Generation as a Testbed for Text Consolidation
In this paper, we suggest revisiting the sentence union generation task as an effective well-defined testbed for assessing text consolidation capabilities, decoupling the consolidation challenge from subjective content selection.
Description-Based Text Similarity
Identifying texts with a given semantics is central for many information seeking scenarios.
Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design
Disagreement in natural language annotation has mostly been studied from a perspective of biases introduced by the annotators and the annotation frameworks.
ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
Context is everything, even in commonsense moral reasoning.
Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE
We hypothesize that to perform this task well, the reader needs to mentally elaborate the scene being described to identify a sensible meaning of the language.
QASem Parsing: Text-to-text Modeling of QA-based Semantics
Several recent works have suggested to represent semantic relations with questions and answers, decomposing textual information into separate interrogative natural language statements.
Asking It All: Generating Contextualized Questions for any Semantic Role
We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage.
Draw Me a Flower: Processing and Grounding Abstraction in Natural Language
Abstraction is a core tenet of human cognition and communication.
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
Modality is the linguistic ability to describe events with added information such as how desirable, plausible, or feasible they are.
QANom: Question-Answer driven SRL for Nominalizations
We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom.
QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding.
Discourse Relations and Conjoined VPs: Automated Sense Recognition
Sense classification of discourse relations is a sub-task of shallow discourse parsing.
