Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning. We use Lean, a theorem proving framework, to address these challenges. By formalizing logical reasoning problems into theorems within Lean, we can solve them by proving or disproving the corresponding theorems. This method reduces the risk of logical inconsistencies with the help of Lean's symbolic solver. It also enhances our ability to treat complex reasoning tasks by using Lean's extensive library of theorem proofs. Our method achieves state-of-the-art performance on the FOLIO dataset and achieves performance near this level on ProofWriter. Notably, these results were accomplished by fine-tuning on fewer than 100 in-domain samples for each dataset.
In this paper, we investigate the interplay between attention heads and specialized "next-token" neurons in the Multilayer Perceptron that predict specific tokens. By prompting an LLM like GPT-4 to explain these model internals, we can elucidate attention mechanisms that activate certain next-token neurons. Our analysis identifies attention heads that recognize contexts relevant to predicting a particular token, activating the associated neuron through the residual connection. We focus specifically on heads in earlier layers consistently activating the same next-token neuron across similar prompts. Exploring these differential activation patterns reveals that heads that specialize for distinct linguistic contexts are tied to generating certain tokens. Overall, our method combines neural explanations and probing isolated components to illuminate how attention enables context-dependent, specialized processing in LLMs.
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them. In this paper, we aim to enforce cohesion whilst controlling for informativeness and redundancy in summaries, in cases where the input exhibits high redundancy. The pipeline controls for redundancy in long inputs as it is consumed, and balances informativeness and cohesion during sentence selection. Our sentence selector simulates human memory to keep track of topics --modeled as lexical chains--, enforcing cohesive ties between noun phrases. Across a variety of domains, our experiments revealed that it is possible to extract highly cohesive summaries that nevertheless read as informative to humans as summaries extracted by only accounting for informativeness or redundancy. The extracted summaries exhibit smooth topic transitions between sentences as signaled by lexical chains, with chains spanning adjacent or near-adjacent sentences.
In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts, and lay summaries. By controlling stylistic features, we find that non-fine-tuned LLMs outperform humans in the MuP review generation task, both in terms of similarity to reference summaries and human preferences. Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed. However, our results also indicate that LLMs cannot consistently generate long summaries with more than 8 sentences. Furthermore, these models exhibit limited capacity to produce highly abstractive lay summaries. Although LLMs demonstrate strong generic summarization competency, sophisticated content control without costly fine-tuning remains an open problem for domain-specific applications.
Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To investigate this, we evaluate concept relearning in models by tracking concept saliency and similarity in pruned neurons during retraining. Our findings reveal that models can quickly regain performance post-pruning by relocating advanced concepts to earlier layers and reallocating pruned concepts to primed neurons with similar semantics. This demonstrates that models exhibit polysemantic capacities and can blend old and new concepts in individual neurons. While neuron pruning provides interpretability into model concepts, our results highlight the challenges of permanent concept removal for improved model \textit{safety}. Monitoring concept reemergence and developing techniques to mitigate relearning of unsafe concepts will be important directions for more robust model editing. Overall, our work strongly demonstrates the resilience and fluidity of concept representations in LLMs post concept removal.
We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics. AMR parsers now obtain high scores on the standard AMR evaluation metric Smatch, close to or even above reported inter-annotator agreement. But that does not mean that AMR parsing is solved; in fact, human evaluation in previous work indicates that current parsers still quite frequently make errors on node labels or graph structure that substantially distort sentence meaning. Here, we provide an evaluation suite that tests AMR parsers on a range of phenomena of practical, technical, and linguistic interest. Our 36 categories range from seen and unseen labels, to structural generalization, to coreference. GrAPES reveals in depth the abilities and shortcomings of current AMR parsers.
Are Large language models (LLMs) temporally grounded? Since LLMs cannot perceive and interact with the environment, it is impossible to answer this question directly. Instead, we provide LLMs with textual narratives and probe them with respect to their common-sense knowledge of the structure and duration of events, their ability to order events along a timeline, and self-consistency within their temporal model (e.g., temporal relations such as after and before are mutually exclusive for any pair of events). We evaluate state-of-the-art LLMs (such as LLaMA 2 and GPT-4) on three tasks reflecting these abilities. Generally, we find that LLMs lag significantly behind both human performance as well as small-scale, specialised LMs. In-context learning, instruction tuning, and chain-of-thought prompting reduce this gap only to a limited degree. Crucially, LLMs struggle the most with self-consistency, displaying incoherent behaviour in at least 27.23% of their predictions. Contrary to expectations, we also find that scaling the model size does not guarantee positive gains in performance. To explain these results, we study the sources from which LLMs may gather temporal information: we find that sentence ordering in unlabelled texts, available during pre-training, is only weakly correlated with event ordering. Moreover, public instruction tuning mixtures contain few temporal tasks. Hence, we conclude that current LLMs lack a consistent temporal model of textual narratives. Code, datasets, and LLM outputs are available at https://github.com/yfqiu-nlp/temporal-llms.
Neural knowledge-to-text generation models often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the given facts, or describe facts not present in the input. To reduce hallucinations, we propose a novel decoding method, TWEAK (Think While Effectively Articulating Knowledge). TWEAK treats the generated sequences at each decoding step and its future sequences as hypotheses, and ranks each generation candidate based on how well their corresponding hypotheses support the input facts using a Hypothesis Verification Model (HVM). We first demonstrate the effectiveness of TWEAK by using a Natural Language Inference (NLI) model as the HVM and report improved faithfulness with minimal impact on the quality. We then replace the NLI model with our task-specific HVM trained with a first-of-a-kind dataset, FATE (Fact-Aligned Textual Entailment), which pairs input facts with their faithful and hallucinated descriptions with the hallucinated spans marked. The new HVM improves the faithfulness and the quality further and runs faster. Overall the best TWEAK variants improve on average 2.22/7.17 points on faithfulness measured by FactKB over WebNLG and TekGen/GenWiki, respectively, with only 0.14/0.32 points degradation on quality measured by BERTScore over the same datasets. Since TWEAK is a decoding-only approach, it can be integrated with any neural generative model without retraining.
Although large language models (LLMs) exhibit remarkable capacity to leverage in-context demonstrations, it is still unclear to what extent they can learn new concepts or facts from ground-truth labels. To address this question, we examine the capacity of instruction-tuned LLMs to follow in-context concept guidelines for sentence labeling tasks. We design guidelines that present different types of factual and counterfactual concept definitions, which are used as prompts for zero-shot sentence classification tasks. Our results show that although concept definitions consistently help in task performance, only the larger models (with 70B parameters or more) have limited ability to work under counterfactual contexts. Importantly, only proprietary models such as GPT-3.5 and GPT-4 can recognize nonsensical guidelines, which we hypothesize is due to more sophisticated alignment methods. Finally, we find that Falcon-180B-chat is outperformed by Llama-2-70B-chat is most cases, which indicates that careful fine-tuning is more effective than increasing model scale. Altogether, our simple evaluation method reveals significant gaps in concept understanding between the most capable open-source language models and the leading proprietary APIs.
We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a joint manner. Using this tool, we study to what extent and how morphosyntactic features are reflected in the representations learned by multilingual pre-trained models. We conduct a large-scale empirical study of over 33 languages and 17 morphosyntactic categories. Our findings demonstrate variations in the encoding of morphosyntactic information across upper and lower layers, with category-specific differences influenced by language properties. Hierarchical clustering of the factorization outputs yields a tree structure that is related to phylogenetic trees manually crafted by linguists. Moreover, we find the factorization outputs exhibit strong associations with performance observed across different cross-lingual tasks. We release our code to facilitate future research.